Web Scraping using SkyTrax

Installing necessary packages to extract HTML elements from the website

#install.packages("rvest") #allows us to parse HTML content and extract the HTML elements from it. 
#install.packages("xml2")
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.0     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.1     ✔ tibble    3.1.8
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.1     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors

library(xml2) 
library(rvest)

## 
## Attaching package: 'rvest'
## 
## The following object is masked from 'package:readr':
## 
##     guess_encoding

library(ggplot2)

Extracting customer reviews from Skytrax website related to Delta Airlines

base_url_1 <- 'https://www.airlinequality.com/airline-reviews/delta-air-lines/'
base_url_2 <- '?sortby=post_date%3ADesc&pagesize=100'

# The website has all customer reviews for Delta Airlines

url_2 <- 'page/2/'
url_3 <- 'page/3/'
url_4 <- 'page/4/'
url_5 <- 'page/5/'
url_6 <- 'page/6/'
url_7 <- 'page/7/'
url_8 <- 'page/8/'
url_9 <- 'page/9/'
url_10 <- 'page/10/'
url_11 <- 'page/11/'
url_12 <- 'page/12/'
url_13 <- 'page/13/'
url_14 <- 'page/14/'
url_15 <- 'page/15/'
url_16 <- 'page/16/'
url_17 <- 'page/17/'
url_18 <- 'page/18/'
url_19 <- 'page/19/'
url_20 <- 'page/20/'
url_21 <- 'page/21/'
url_22 <- 'page/22/'
url_23 <- 'page/23/'
url_24 <- 'page/24/'
url_25 <- 'page/25/'
url_26 <- 'page/26/'
url_27 <- 'page/27/'

full_url_1 <- base::paste0(base_url_1, base_url_2)
full_url_2 <- base::paste0(base_url_1, url_2, base_url_2)
full_url_3 <- base::paste0(base_url_1, url_3, base_url_2)
full_url_4 <- base::paste0(base_url_1, url_4, base_url_2)
full_url_5 <- base::paste0(base_url_1, url_5, base_url_2)
full_url_6 <- base::paste0(base_url_1, url_6, base_url_2)
full_url_7 <- base::paste0(base_url_1, url_7, base_url_2)
full_url_8 <- base::paste0(base_url_1, url_8, base_url_2)
full_url_9 <- base::paste0(base_url_1, url_9, base_url_2)
full_url_10 <- base::paste0(base_url_1, url_10, base_url_2)
full_url_11 <- base::paste0(base_url_1, url_11, base_url_2)
full_url_12 <- base::paste0(base_url_1, url_12, base_url_2)
full_url_13 <- base::paste0(base_url_1, url_13, base_url_2)
full_url_14 <- base::paste0(base_url_1, url_14, base_url_2)
full_url_15 <- base::paste0(base_url_1, url_15, base_url_2)
full_url_16 <- base::paste0(base_url_1, url_16, base_url_2)
full_url_17 <- base::paste0(base_url_1, url_17, base_url_2)
full_url_18 <- base::paste0(base_url_1, url_18, base_url_2)
full_url_19 <- base::paste0(base_url_1, url_19, base_url_2)
full_url_20 <- base::paste0(base_url_1, url_20, base_url_2)
full_url_21 <- base::paste0(base_url_1, url_21, base_url_2)
full_url_22 <- base::paste0(base_url_1, url_22, base_url_2)
full_url_23 <- base::paste0(base_url_1, url_23, base_url_2)
full_url_24 <- base::paste0(base_url_1, url_24, base_url_2)
full_url_25 <- base::paste0(base_url_1, url_25, base_url_2)
full_url_26 <- base::paste0(base_url_1, url_26, base_url_2)
full_url_27 <- base::paste0(base_url_1, url_27, base_url_2)

library(rvest)
page_1 <- full_url_1 %>% read_html()  
page_2 <- full_url_2 %>% read_html()
page_3 <- full_url_3 %>% read_html()  
page_4 <- full_url_4 %>% read_html()
page_5 <- full_url_5 %>% read_html()  
page_6 <- full_url_6 %>% read_html()
page_7 <- full_url_7 %>% read_html()  
page_8 <- full_url_8 %>% read_html()
page_9 <- full_url_9 %>% read_html()  
page_10 <- full_url_10 %>% read_html()
page_11 <- full_url_11 %>% read_html()  
page_12 <- full_url_12 %>% read_html()
page_13 <- full_url_13 %>% read_html()  
page_14 <- full_url_14 %>% read_html()
page_15 <- full_url_15 %>% read_html()
page_16 <- full_url_16 %>% read_html()
page_17 <- full_url_17 %>% read_html()
page_18 <- full_url_18 %>% read_html()
page_19 <- full_url_19 %>% read_html()
page_20 <- full_url_20 %>% read_html()
page_21 <- full_url_21 %>% read_html()
page_22 <- full_url_22 %>% read_html()
page_23 <- full_url_23 %>% read_html()
page_24 <- full_url_24 %>% read_html()
page_25 <- full_url_25 %>% read_html()
page_26 <- full_url_26 %>% read_html()
page_27 <- full_url_27 %>% read_html()

library(rvest) 

# get customer reviews starting from Page 1...27
reviews_data_1 <- page_1 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_2 <- page_2 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_3 <- page_3 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_4 <- page_4 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_5 <- page_5 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_6 <- page_6 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_7 <- page_7 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_8 <- page_8 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_9 <- page_9 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_10 <- page_10 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_11 <- page_11 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_12 <- page_12 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_13 <- page_13 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_14 <- page_14 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_15 <- page_15 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_16 <- page_16 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_17 <- page_17 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_18 <- page_18 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_19 <- page_19 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_20 <- page_20 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_21 <- page_21 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_22 <- page_22 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_23 <- page_23 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_24 <- page_24 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_25 <- page_25 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_26 <- page_26 %>% html_element(css = '.position-content') %>% html_table()
reviews_data_27 <- page_27 %>% html_element(css = '.position-content') %>% html_table()

reviews_data_text_content_page_1 <- html_nodes(page_1, ".text_content") %>% html_text()
reviews_data_text_content_page_2 <- html_nodes(page_2, ".text_content") %>% html_text()
reviews_data_text_content_page_3 <- html_nodes(page_3, ".text_content") %>% html_text()
reviews_data_text_content_page_4 <- html_nodes(page_4, ".text_content") %>% html_text()
reviews_data_text_content_page_5 <- html_nodes(page_5, ".text_content") %>% html_text()
reviews_data_text_content_page_6 <- html_nodes(page_6, ".text_content") %>% html_text()
reviews_data_text_content_page_7 <- html_nodes(page_7, ".text_content") %>% html_text()
reviews_data_text_content_page_8 <- html_nodes(page_8, ".text_content") %>% html_text()
reviews_data_text_content_page_9 <- html_nodes(page_9, ".text_content") %>% html_text()
reviews_data_text_content_page_10 <- html_nodes(page_10, ".text_content") %>% html_text()
reviews_data_text_content_page_11 <- html_nodes(page_11, ".text_content") %>% html_text()
reviews_data_text_content_page_12 <- html_nodes(page_12, ".text_content") %>% html_text()
reviews_data_text_content_page_13 <- html_nodes(page_13, ".text_content") %>% html_text()
reviews_data_text_content_page_14 <- html_nodes(page_14, ".text_content") %>% html_text()
reviews_data_text_content_page_15 <- html_nodes(page_15, ".text_content") %>% html_text()
reviews_data_text_content_page_16 <- html_nodes(page_16, ".text_content") %>% html_text()
reviews_data_text_content_page_17 <- html_nodes(page_17, ".text_content") %>% html_text()
reviews_data_text_content_page_18 <- html_nodes(page_18, ".text_content") %>% html_text()
reviews_data_text_content_page_19 <- html_nodes(page_19, ".text_content") %>% html_text()
reviews_data_text_content_page_20 <- html_nodes(page_20, ".text_content") %>% html_text()
reviews_data_text_content_page_21 <- html_nodes(page_21, ".text_content") %>% html_text()
reviews_data_text_content_page_22 <- html_nodes(page_22, ".text_content") %>% html_text()
reviews_data_text_content_page_23 <- html_nodes(page_23, ".text_content") %>% html_text()
reviews_data_text_content_page_24 <- html_nodes(page_24, ".text_content") %>% html_text()
reviews_data_text_content_page_25 <- html_nodes(page_25, ".text_content") %>% html_text()
reviews_data_text_content_page_26 <- html_nodes(page_26, ".text_content") %>% html_text()
reviews_data_text_content_page_27 <- html_nodes(page_27, ".text_content") %>% html_text()

text_reviews_1 <- data.frame(reviews_data_text_content_page_1)
text_reviews_2 <- data.frame(reviews_data_text_content_page_2)
text_reviews_3 <- data.frame(reviews_data_text_content_page_3)
text_reviews_4 <- data.frame(reviews_data_text_content_page_4)
text_reviews_5 <- data.frame(reviews_data_text_content_page_5)
text_reviews_6 <- data.frame(reviews_data_text_content_page_6)
text_reviews_7 <- data.frame(reviews_data_text_content_page_7)
text_reviews_8 <- data.frame(reviews_data_text_content_page_8)
text_reviews_9 <- data.frame(reviews_data_text_content_page_9)
text_reviews_10 <- data.frame(reviews_data_text_content_page_10)
text_reviews_11 <- data.frame(reviews_data_text_content_page_1)
text_reviews_12 <- data.frame(reviews_data_text_content_page_2)
text_reviews_13 <- data.frame(reviews_data_text_content_page_3)
text_reviews_14 <- data.frame(reviews_data_text_content_page_4)
text_reviews_15 <- data.frame(reviews_data_text_content_page_5)
text_reviews_16 <- data.frame(reviews_data_text_content_page_6)
text_reviews_17 <- data.frame(reviews_data_text_content_page_7)
text_reviews_18 <- data.frame(reviews_data_text_content_page_8)
text_reviews_19 <- data.frame(reviews_data_text_content_page_9)
text_reviews_20 <- data.frame(reviews_data_text_content_page_10)
text_reviews_21 <- data.frame(reviews_data_text_content_page_1)
text_reviews_22 <- data.frame(reviews_data_text_content_page_2)
text_reviews_23 <- data.frame(reviews_data_text_content_page_3)
text_reviews_24 <- data.frame(reviews_data_text_content_page_4)
text_reviews_25 <- data.frame(reviews_data_text_content_page_5)
text_reviews_26 <- data.frame(reviews_data_text_content_page_6)
text_reviews_27 <- data.frame(reviews_data_text_content_page_7)

colnames(text_reviews_1) <- c("Reviews")
colnames(text_reviews_2) <- c("Reviews")
colnames(text_reviews_3) <- c("Reviews")
colnames(text_reviews_4) <- c("Reviews")
colnames(text_reviews_5) <- c("Reviews")
colnames(text_reviews_6) <- c("Reviews")
colnames(text_reviews_7) <- c("Reviews")
colnames(text_reviews_8) <- c("Reviews")
colnames(text_reviews_9) <- c("Reviews")
colnames(text_reviews_10) <- c("Reviews")
colnames(text_reviews_11) <- c("Reviews")
colnames(text_reviews_12) <- c("Reviews")
colnames(text_reviews_13) <- c("Reviews")
colnames(text_reviews_14) <- c("Reviews")
colnames(text_reviews_15) <- c("Reviews")
colnames(text_reviews_16) <- c("Reviews")
colnames(text_reviews_17) <- c("Reviews")
colnames(text_reviews_18) <- c("Reviews")
colnames(text_reviews_19) <- c("Reviews")
colnames(text_reviews_20) <- c("Reviews")
colnames(text_reviews_21) <- c("Reviews")
colnames(text_reviews_22) <- c("Reviews")
colnames(text_reviews_23) <- c("Reviews")
colnames(text_reviews_24) <- c("Reviews")
colnames(text_reviews_25) <- c("Reviews")
colnames(text_reviews_26) <- c("Reviews")
colnames(text_reviews_27) <- c("Reviews")

text_reviews <- rbind(text_reviews_1, text_reviews_2, text_reviews_3, text_reviews_4, text_reviews_5, text_reviews_6, text_reviews_7, text_reviews_8, text_reviews_9, text_reviews_10,text_reviews_11, text_reviews_12, text_reviews_13, text_reviews_14, text_reviews_15, text_reviews_16, text_reviews_17, text_reviews_18, text_reviews_19, text_reviews_20,text_reviews_21, text_reviews_22, text_reviews_23, text_reviews_24, text_reviews_25, text_reviews_26, text_reviews_27)

text_reviews <- data.frame(text_reviews)  
text_reviews <- text_reviews[-c(2160:2700), ]
text_reviews <- data.frame(text_reviews) 
colnames(text_reviews) <- c("Reviews")

# Extracting star ratings from page 1
star_rating_elements_page_1 <- html_nodes(page_1, ".star.fill")
star_rating_elements_page_2 <- html_nodes(page_2, ".star.fill")
star_rating_elements_page_3 <- html_nodes(page_3, ".star.fill")
star_rating_elements_page_4 <- html_nodes(page_4, ".star.fill")
star_rating_elements_page_5 <- html_nodes(page_5, ".star.fill")
star_rating_elements_page_6 <- html_nodes(page_6, ".star.fill")
star_rating_elements_page_7 <- html_nodes(page_7, ".star.fill")
star_rating_elements_page_8 <- html_nodes(page_8, ".star.fill")
star_rating_elements_page_9 <- html_nodes(page_9, ".star.fill")
star_rating_elements_page_10 <- html_nodes(page_10, ".star.fill")
star_rating_elements_page_11 <- html_nodes(page_11, ".star.fill")
star_rating_elements_page_12 <- html_nodes(page_12, ".star.fill")
star_rating_elements_page_13 <- html_nodes(page_13, ".star.fill")
star_rating_elements_page_14 <- html_nodes(page_14, ".star.fill")
star_rating_elements_page_15 <- html_nodes(page_15, ".star.fill")
star_rating_elements_page_16 <- html_nodes(page_16, ".star.fill")
star_rating_elements_page_17 <- html_nodes(page_17, ".star.fill")
star_rating_elements_page_18 <- html_nodes(page_18, ".star.fill")
star_rating_elements_page_19 <- html_nodes(page_19, ".star.fill")
star_rating_elements_page_20 <- html_nodes(page_20, ".star.fill")
star_rating_elements_page_21 <- html_nodes(page_21, ".star.fill")
star_rating_elements_page_22 <- html_nodes(page_22, ".star.fill")
star_rating_elements_page_23 <- html_nodes(page_23, ".star.fill")
star_rating_elements_page_24 <- html_nodes(page_24, ".star.fill")
star_rating_elements_page_25 <- html_nodes(page_25, ".star.fill")
star_rating_elements_page_26 <- html_nodes(page_26, ".star.fill")
star_rating_elements_page_27 <- html_nodes(page_27, ".star.fill")


star_ratings_page_1 <- sapply(star_rating_elements_page_1, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_2 <- sapply(star_rating_elements_page_2, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_3 <- sapply(star_rating_elements_page_3, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_4 <- sapply(star_rating_elements_page_4, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_5 <- sapply(star_rating_elements_page_5, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_6 <- sapply(star_rating_elements_page_6, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_7 <- sapply(star_rating_elements_page_7, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_8 <- sapply(star_rating_elements_page_8, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_9 <- sapply(star_rating_elements_page_9, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_10 <- sapply(star_rating_elements_page_10, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_11 <- sapply(star_rating_elements_page_11, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_12 <- sapply(star_rating_elements_page_12, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_13 <- sapply(star_rating_elements_page_13, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_14 <- sapply(star_rating_elements_page_14, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_15 <- sapply(star_rating_elements_page_15, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_16 <- sapply(star_rating_elements_page_16, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_17 <- sapply(star_rating_elements_page_17, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_18 <- sapply(star_rating_elements_page_18, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_19 <- sapply(star_rating_elements_page_19, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_20 <- sapply(star_rating_elements_page_20, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_21 <- sapply(star_rating_elements_page_21, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_22 <- sapply(star_rating_elements_page_22, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_23 <- sapply(star_rating_elements_page_23, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_24 <- sapply(star_rating_elements_page_24, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_25 <- sapply(star_rating_elements_page_25, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_26 <- sapply(star_rating_elements_page_26, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))
star_ratings_page_27 <- sapply(star_rating_elements_page_27, function(x) as.numeric(gsub("[^0-9.]", "", html_text(x))))


star_ratings_page_1 <- data.frame(star_ratings_page_1)
star_ratings_page_2 <- data.frame(star_ratings_page_2)
star_ratings_page_3 <- data.frame(star_ratings_page_3)
star_ratings_page_4 <- data.frame(star_ratings_page_4)
star_ratings_page_5 <- data.frame(star_ratings_page_5)
star_ratings_page_6 <- data.frame(star_ratings_page_6)
star_ratings_page_7 <- data.frame(star_ratings_page_7)
star_ratings_page_8 <- data.frame(star_ratings_page_8)
star_ratings_page_9 <- data.frame(star_ratings_page_9)
star_ratings_page_10 <- data.frame(star_ratings_page_10)
star_ratings_page_11 <- data.frame(star_ratings_page_11)
star_ratings_page_12 <- data.frame(star_ratings_page_12)
star_ratings_page_13 <- data.frame(star_ratings_page_13)
star_ratings_page_14 <- data.frame(star_ratings_page_14)
star_ratings_page_15 <- data.frame(star_ratings_page_15)
star_ratings_page_16 <- data.frame(star_ratings_page_16)
star_ratings_page_17 <- data.frame(star_ratings_page_17)
star_ratings_page_18 <- data.frame(star_ratings_page_18)
star_ratings_page_19 <- data.frame(star_ratings_page_19)
star_ratings_page_20 <- data.frame(star_ratings_page_20)
star_ratings_page_21 <- data.frame(star_ratings_page_21)
star_ratings_page_22 <- data.frame(star_ratings_page_22)
star_ratings_page_23 <- data.frame(star_ratings_page_23)
star_ratings_page_24 <- data.frame(star_ratings_page_24)
star_ratings_page_25 <- data.frame(star_ratings_page_25)
star_ratings_page_26 <- data.frame(star_ratings_page_26)
star_ratings_page_27 <- data.frame(star_ratings_page_27)

colnames(star_ratings_page_1) <- c("Ratings")
colnames(star_ratings_page_2) <- c("Ratings")
colnames(star_ratings_page_3) <- c("Ratings")
colnames(star_ratings_page_4) <- c("Ratings")
colnames(star_ratings_page_5) <- c("Ratings")
colnames(star_ratings_page_6) <- c("Ratings")
colnames(star_ratings_page_7) <- c("Ratings")
colnames(star_ratings_page_8) <- c("Ratings")
colnames(star_ratings_page_9) <- c("Ratings")
colnames(star_ratings_page_10) <- c("Ratings")
colnames(star_ratings_page_11) <- c("Ratings")
colnames(star_ratings_page_12) <- c("Ratings")
colnames(star_ratings_page_13) <- c("Ratings")
colnames(star_ratings_page_14) <- c("Ratings")
colnames(star_ratings_page_15) <- c("Ratings")
colnames(star_ratings_page_16) <- c("Ratings")
colnames(star_ratings_page_17) <- c("Ratings")
colnames(star_ratings_page_18) <- c("Ratings")
colnames(star_ratings_page_19) <- c("Ratings")
colnames(star_ratings_page_20) <- c("Ratings")
colnames(star_ratings_page_21) <- c("Ratings")
colnames(star_ratings_page_22) <- c("Ratings")
colnames(star_ratings_page_23) <- c("Ratings")
colnames(star_ratings_page_24) <- c("Ratings")
colnames(star_ratings_page_25) <- c("Ratings")
colnames(star_ratings_page_26) <- c("Ratings")
colnames(star_ratings_page_27) <- c("Ratings")

# Joining the data frames to make it easier for for-loop
final_ratings<- rbind(star_ratings_page_1, star_ratings_page_2, star_ratings_page_3, star_ratings_page_4, star_ratings_page_5, star_ratings_page_6, star_ratings_page_7, star_ratings_page_8, star_ratings_page_9, star_ratings_page_10, star_ratings_page_11, star_ratings_page_12, star_ratings_page_13, star_ratings_page_14, star_ratings_page_15, star_ratings_page_16, star_ratings_page_17, star_ratings_page_18, star_ratings_page_19, star_ratings_page_20, star_ratings_page_21, star_ratings_page_22, star_ratings_page_23, star_ratings_page_24, star_ratings_page_25, star_ratings_page_26, star_ratings_page_27)

colnames(final_ratings) <- c("Ratings")

provisional_data <- rbind(reviews_data_1, reviews_data_2, reviews_data_3, reviews_data_4, reviews_data_5, reviews_data_6, reviews_data_7, reviews_data_8, reviews_data_9, reviews_data_10, reviews_data_11, reviews_data_12, reviews_data_13, reviews_data_14, reviews_data_15, reviews_data_16, reviews_data_17, reviews_data_18, reviews_data_19, reviews_data_20, reviews_data_21, reviews_data_22, reviews_data_23, reviews_data_24, reviews_data_25, reviews_data_26, reviews_data_27)

# final_data <- final_data[!grepl("Aircraft", final_data_till_page_10$X1),]

# Removing reviews that have incomplete information, since it is making an issue with data wrangling, although it's an inefficient way, that's the best solution so far, will try and add them later on.

# final_data_till_page_10 <- final_data_till_page_10[-c(1:11, 60:70, 83:93, 142:152, 165:175, 188:195, 220:260, 273:283, 308:314, 327:344, 381:399, 424:433, 446:452, 465:473, 486:551, 564:573, 610:618, 655:665, 726:734, 747:757, 794:804, 841:850, 875:901, 938:946, 1043:1051, 1088:1096, 1109:1119, 1156:1176, 1189:1199, 1212:1248, 1261:1275, 1300:1318, 1343:1379, 1404:1414, 1427:1443, 1468:1478, 1515:1534, 1547:1553, 1566:1582, 1619:1649, 1662:1677, 1690:1698, 1711:1720, 1733:1742, 1803:1811, 1824:1833, 1858:1873, 1910:1918, 1931:1941, 1954:1974, 2011:2026, 2051:2078, 2091:2101, 2114:2119, 2192:2213, 2262:2280, 2305:2314, 2327:2335, 2360:2394, 2419:2437, 2450:2465, 2478:2486, 2511:2536, 2585:2591, 2604:2614, 2627:2645, 2658:2664, 2701:2742, 2755:2763, 2812:2822, 2847:2865, 2890:2923, 2972:2978, 3027:3044, 3057:3065, 3078:3088, 3101:3113, 3150:3158, 3183:3198, 3211:3221, 3246:3256, 3269:3287, 3300:3345, 3406:3414, 3439:3449, 3474:3489, 3514:3531, 3556:3564, 3625:3639, 3664:3697, 3794:3804, 3853:3878, 3891:3900, 3925:3955, 3968:3978, 4087:4105, 4130:4139, 4152:4183, 4196:4216, 4241:4254, 4267:4275, 4336:4354, 4379:4388, 4437:4445, 4458:4496, 4509:4528, 4577:4585, 4598:4632, 4657:4665, 4702:4723, 4772:4820, 4845:4855, 4868:4893, 4918:4939, 4952:4962, 4975:5036, 5073:5083, 5132:5177, 5226:5272, 5297:5331, 5368:5397, 5410:5447, 5472:5480, 5493:5497, 5522:5532, 5545:5610, 5635:5654, 5703:5727, 5752:5760, 5773:5811, 5824:5852, 5865:5893, 5906:5916, 5941:5968, 5981:5991, 6040:6060, 6073:6120, 6133:6153, 6166:6183, 6208:6218, 6243:6267, 6292:6302, 6315:6323, 6360:6370, 6419:6445, 6482:6492, 6553:6561, 6574:6594, 6631:6636, 6649:6653, 6666:6675, 6712:6726, 6739:6793, 6842:6850, 6875:6883, 6908:6913, 6986:7023, 7036:10638 ),]

#final_data_till_page_10 <- final_data_till_page_10[-c(37:47, 60:70, 119:129, 142:152, 165:172, 197:237, 250:260, 285:291, 304:321, 358:366, 367:376, 401:410, 423:429, 442:450, 463:528, 541:550, 587:595, 632:642, 703:711, 724:734, 771:781, 818:827, 852:878, 915:923, 1020:1028, 1065:1073, 1086:1096, 1133:1153, 1166:1176, 1189:1225, 1238:1252, 1277:1295, 1320:1356, 1381:1391, 1404:1420, 1445:1455, 1492:1511, 1524:1530, 1543:1559, 1596:1626, 1639:1654, 1667:1675, 1688:1697, 1710:1719, 1780:1788, 1801:1810, 1835:1850, 1887:1895, 1908:1918, 1931:1951, 1988:2003, 2028:2055, 2068:2078, 2091:2096),]

EDA: Data Wrangling for Reviews

# 
# # Data Wrangling for every X1 attribute; since the data is in vertical format it is necessary to make it in record format for further analysis
# reviews_final_data <- data.frame(matrix(ncol = 13, nrow = 3000), stringsAsFactors = FALSE)
# colnames(reviews_final_data) <- c('Aircraft', 'Type Of Traveller', 'Seat Type', 'Route','Date Flown', 'Seat Comfort', 'Cabin Staff Service', 'Food & Beverages', 'Inflight Entertainment', 'Ground Service', 'Wifi & Connectivity', 'Value For Money', 'Recommended')
# ir = 1
# ic = 1
# for(i in 1:nrow(provisional_data)){
#    if(ic >= 14){
#      ir = ir+1
#      ic <- 1
#    }
#   if(ic==1){
#     if(grepl("Aircraft", provisional_data$X1[i] == TRUE)){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     } else{
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 2){
#     if(grepl("Type Of Traveller", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     }else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 3){
#     if(grepl("Seat Type", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     } else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 4){
#     if(grepl("Route", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     }else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   }
#   if(ic == 5){
#     if(grepl("Date Flown", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     }else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 6){
#     if(grepl("Seat Comfort", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     }else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 7){
#     if(grepl("Cabin Staff Service", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     }else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 8){
#     if(grepl("Food & Beverages", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     }else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 9){
#     if(grepl("Inflight Entertainment", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     }else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 10){
#     if(grepl("Ground Service", provisional_data$X1[i]) == TRUE){
#       reviews_final_data[ir,ic] = provisional_data$X2[i]
#       i = i + 1
#     }else {
#       reviews_final_data[ir,ic] = "9999"
#     }
#     ic = ic + 1
#   } 
#   if(ic == 11){
#     if(grepl("Wifi & Connectivity", provisional_data$X1[i]) == TRUE){
# #       reviews_final_data[ir,ic] = provisional_data$X2[i]
# #       i = i + 1
# #     }else {
# #       reviews_final_data[ir,ic] = "9999"
# #     }
# #     ic = ic + 1
# #   } 
# #   if(ic == 12){
# #     if(grepl("Value For Money", provisional_data$X1[i]) == TRUE){
# #       reviews_final_data[ir,ic] = provisional_data$X2[i]
# #       i = i + 1
# #     }else {
# #       reviews_final_data[ir,ic] = "9999"
# #     }
# #     ic = ic + 1
# #   } 
# #   if (ic == 13){
# #     if(grepl("Recommended", provisional_data$X1[i]) == TRUE){
# #       reviews_final_data[ir,ic] = provisional_data$X2[i]
# #       i = i + 1
# #     }else {
# #       reviews_final_data[ir,ic] = "9999"
# #     }
# #     ic = ic + 1
# #   }
# # 
# # }
# 
# # Define the column order based on column names
# column_order <- c("Aircraft", "Type Of Traveller", "Seat Type", "Route",
#                   "Date Flown", "Seat Comfort", "Cabin Staff Service",
#                   "Food & Beverages", "Inflight Entertainment", "Ground Service",
#                   "Wifi & Connectivity", "Value For Money", "Recommended")
# 
# # Initialize the output data frame with 9999 values
# reviews_final_data <- data.frame(matrix(rep("9999", length(column_order) * nrow(provisional_data)),
#                                         nrow = nrow(provisional_data),
#                                         ncol = length(column_order),
#                                         dimnames = list(NULL, column_order)))
# 
# # Loop through the input data and fill in the output data frame
# ic <- 1
# ir <- 1
# for (i in 1:nrow(provisional_data)) {
#   if (ic > length(column_order)) {
#     ir <- ir + 1
#     ic <- 1
#   }
#   if (grepl(column_order[ic], provisional_data$X1[i])) {
#     reviews_final_data[ir, ic] <- provisional_data$X2[i]
#     ic <- ic + 1
#   }
# }


# Code iteration perfected
# Initialize reviews_final_data with "9999"
reviews_final_data <- matrix(ncol = 13, nrow = 2159)
# Loop through each row of provisional_data and populate reviews_final_data
ir <- 1
ic <- 1
for(i in 1:nrow(provisional_data)){
  
  # Check if ic is greater than or equal to 14
  if(ic >= 14){
    ir <- ir + 1
    ic <- 1
  }
  
  # Populate the corresponding element of reviews_final_data based on the column header
  if(provisional_data$X1[i] == "Aircraft"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 1] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Type Of Traveller"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 2] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Seat Type"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 3] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Route"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 4] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Date Flown"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 5] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Seat Comfort"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 6] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Cabin Staff Service"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 7] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Food & Beverages"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 8] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Inflight Entertainment"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 9] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Ground Service"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 10] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Wifi & Connectivity"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 11] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Value For Money"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 12] <- provisional_data$X2[i]
  } else if(provisional_data$X1[i] == "Recommended"){
    if(ir > 2159)
  {
    break
  }
    reviews_final_data[ir, 13] <- provisional_data$X2[i]
  }
  
  # Increment ic
  ic <- ic + 1
}



# Removing the columns since they do not make any sense, we have separate star ratings columns that have been implemented below.
reviews_final_data <- reviews_final_data[,-c(6:12)]
reviews_final_data <- data.frame(reviews_final_data)
colnames(reviews_final_data) <- c("Aircraft", "Type.Of.Traveller", "Seat.Type", "Route", "Date Flown", "Recommended")

EDA: Data Wrangling for Star Ratings

#Data Wrangling for Star Ratings
revised_ratings <- data.frame(matrix(ncol = 7, nrow = 2159))
colnames(revised_ratings) <- c('Seat Comfort', 'Cabin Staff Service', 'Food & Beverages', 'Inflight Entertainment', 'Ground Service', 'Wifi & Connectivity', 'Value For Money')
ir = 1
ic = 1
for(i in 1:nrow(final_ratings)) {       # for-loop over columns
 revised_ratings[ir, ic] <- final_ratings[i, 1]
    if (i%%7==0) {
      ir <- ir+1
      ic <- 1
    }
    else if(ir == 2160){
      break
  } else {
      ic <- ic+1
    }

}

revised_ratings <- revised_ratings[-2160,]

Data Integration

# Combining the three data frames  (signifies other attributes apart from star ratings), revised_ratings (signifies star ratings), and text_reviews_till_page_10 (Signifies customer reviews)
reviews <- cbind(reviews_final_data, revised_ratings, text_reviews)

Data Cleaning

library(magrittr)

## 
## Attaching package: 'magrittr'

## The following object is masked from 'package:purrr':
## 
##     set_names

## The following object is masked from 'package:tidyr':
## 
##     extract

# Adding a new column to calculate the total score
ratings_cols <- c("Seat Comfort", "Cabin Staff Service", "Food & Beverages",
                  "Inflight Entertainment", "Ground Service", "Wifi & Connectivity", "Value For Money")

# Add up the values in the five columns and calculate the mean
  reviews <- reviews %>% mutate(`Total Rating` = rowSums(reviews[, ratings_cols])/7)

# The reviews column has a shabby format, for example the review has the verification before the review starts, we can separately create a verification column to check the integrity of the review
reviews <- reviews %>% mutate(Verification = ifelse(grepl("✅ Trip Verified", Reviews), "Trip Verified", ifelse(grepl("Not Verified", Reviews), "Not Verified", NA)))

# Remove the substring from the original column
reviews$Reviews  <- gsub("✅ Trip Verified \\| ", "", reviews$Reviews)
reviews$Reviews  <- gsub("✅ Trip Verified |", "", reviews$Reviews)
reviews$Reviews <- gsub("Not Verified \\|","", reviews$Reviews)
reviews$Reviews <- gsub("|","",reviews$Reviews)

# We can break down the "Route" column into two parts: "Origin" and "Destination"
library(tidyr)
Route_updated <- data.frame(reviews$Route)
# separate "Route" column into "Origin location" and "Destination"
Route_updated <- separate(Route_updated, col = reviews.Route, into = c("Origin", "Destination"), sep = c(" to "))

## Warning: Expected 2 pieces. Additional pieces discarded in 2 rows [301, 1471].

## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 4 rows [1337, 1752, 1941,
## 1976].

head(Route_updated)

##          Origin            Destination
## 1      New York                   Rome
## 2   Los Angeles              Melbourne
## 3     Cape Town                Atlanta
## 4      San Juan Paris via New York JFK
## 5 Ft Lauderdale                Atlanta
## 6 Ft Lauderdale                Atlanta

reviews <- reviews[,-4]

reviews <- cbind(reviews, Route_updated)

# Formatting the Date Flown column in the Data frame.
class(reviews$`Date Flown`)

## [1] "character"

library(lubridate)
# Convert Date Flown to MM-YY format
reviews$`Date Flown` <- dmy(paste0("01-", reviews$`Date Flown`))

## Warning: 178 failed to parse.

reviews$`Date Flown` <- format(reviews$`Date Flown`, "%m-%y")

head(reviews$`Date Flown`)

## [1] "03-23" "04-23" "03-23" "04-23" "04-23" "04-23"

# Identifying the missing values
cat("There are", sum(is.na(reviews$Aircraft)), "missing data values in 'Aircraft' column.\n")

## There are 1614 missing data values in 'Aircraft' column.

cat("There are", sum(is.na(reviews$Type.Of.Traveller)), "missing data values in 'Type of traveller' column.\n")

## There are 177 missing data values in 'Type of traveller' column.

cat("There are", sum(is.na(reviews$Seat.Type)), "missing data values in 'Seat Type' column.\n")

## There are 0 missing data values in 'Seat Type' column.

cat("There are", sum(is.na(reviews$`Date Flown`)), "missing data values in 'Date Flown' column.\n")

## There are 178 missing data values in 'Date Flown' column.

cat("There are", sum(is.na(reviews$Recommended)), "missing data values in 'Recommended' column.\n")

## There are 0 missing data values in 'Recommended' column.

cat("There are", sum(is.na(reviews$`Seat Comfort`)), "missing data values in 'Seat Comfort' column.\n")

## There are 0 missing data values in 'Seat Comfort' column.

cat("There are", sum(is.na(reviews$`Cabin Staff Service`)), "missing data values in 'Cabin Staff Services' column.\n")

## There are 0 missing data values in 'Cabin Staff Services' column.

cat("There are", sum(is.na(reviews$`Food & Beverages`)), "missing data values in 'Food & Beverages' column.\n")

## There are 0 missing data values in 'Food & Beverages' column.

cat("There are", sum(is.na(reviews$`Inflight Entertainment`)), "missing data values in 'Inflight Entertainment' column.\n")

## There are 0 missing data values in 'Inflight Entertainment' column.

cat("There are", sum(is.na(reviews$`Ground Service`)), "missing data values in 'Ground Service' column.\n")

## There are 0 missing data values in 'Ground Service' column.

cat("There are", sum(is.na(reviews$`Wifi & Connectivity`)), "missing data values in 'Wifi & Connectivity' column.\n")

## There are 0 missing data values in 'Wifi & Connectivity' column.

cat("There are", sum(is.na(reviews$`Value For Money`)), "missing data values in 'Value for Money' column.\n")

## There are 0 missing data values in 'Value for Money' column.

cat("There are", sum(is.na(reviews$Reviews)), "missing data values in 'Reviews' column.\n")

## There are 0 missing data values in 'Reviews' column.

cat("There are", sum(is.na(reviews$Verification)), "missing data values in 'Verification' column.\n")

## There are 5 missing data values in 'Verification' column.

cat("There are", sum(is.na(reviews$Origin)), "missing data values in 'Origin' column.\n")

## There are 187 missing data values in 'Origin' column.

cat("There are", sum(is.na(reviews$Destination)), "missing data values in 'Destination' column.\n")

## There are 191 missing data values in 'Destination' column.

# Removing the 'Aircraft Column' since it doesn't contain any valuable information or there are 1621 missing values.
reviews <- reviews[,-1]

# Replacing the NAs in 'Type of Traveller' to random values from "Solo Leisure", "Couple Leisure", "Family Leisure" and "Business".
reviews$Type.Of.Traveller <- ifelse(is.na(reviews$Type.Of.Traveller), sample(c("Solo Leisure", "Business", "Couple Leisure", "Family Leisure"), 1), reviews$Type.Of.Traveller)

reviews$Seat.Type <- ifelse(is.na(reviews$Seat.Type), sample(c("Economy Class", "First Class", "Premium Economy", "Business Class"),1), reviews$Seat.Type)

# Replacing the NAs in 'Date Flown' to random values between April 2015 to September 2022
months <- seq(from = ymd("2015-04-01"), to = ymd("2022-09-01"), by = "months")
months_str <- format(months, "%m-%y")

reviews$`Date Flown`[is.na(reviews$`Date Flown`)] <- sample(months_str, sum(is.na(reviews$`Date Flown`)), replace = TRUE)

# Replacing both NA values to "Not Verified"
reviews$Verification[is.na(reviews$Verification)] = "Not Verified"

# Origin and Destination NA values cleaning
reviews <- reviews[complete.cases(reviews[c("Origin", "Destination")]),]

# Destination additional locations cleaning
reviews$Final.Destination <- gsub("(.*via\\s)(\\w+)(\\s\\&\\s)(\\w+)(.*)", "\\2, \\4", reviews$Destination)
reviews$Final.Destination <- gsub("(.*via\\s)(\\w+)(.*)", "\\2", reviews$Final.Destination)
reviews <- reviews[,-16]

# Replace specific destination values in Final.Destination column
reviews$Final.Destination <- ifelse(grepl("New", reviews$Final.Destination), "New York",  ifelse(grepl("Salt", reviews$Final.Destination), "Salt Lake City",reviews$Final.Destination))

cat("There are", sum(is.na(reviews$Type.Of.Traveller)), "missing data values in 'Type of traveller' column.\n")

## There are 0 missing data values in 'Type of traveller' column.

cat("There are", sum(is.na(reviews$Seat.Type)), "missing data values in 'Seat Type' column.\n")

## There are 0 missing data values in 'Seat Type' column.

cat("There are", sum(is.na(reviews$Route)), "missing data values in 'Route' column.\n")

## There are 0 missing data values in 'Route' column.

cat("There are", sum(is.na(reviews$`Date Flown`)), "missing data values in 'Date Flown' column.\n")

## There are 0 missing data values in 'Date Flown' column.

cat("There are", sum(is.na(reviews$Recommended)), "missing data values in 'Recommended' column.\n")

## There are 0 missing data values in 'Recommended' column.

cat("There are", sum(is.na(reviews$`Seat Comfort`)), "missing data values in 'Seat Comfort' column.\n")

## There are 0 missing data values in 'Seat Comfort' column.

cat("There are", sum(is.na(reviews$`Cabin Staff Service`)), "missing data values in 'Cabin Staff Services' column.\n")

## There are 0 missing data values in 'Cabin Staff Services' column.

cat("There are", sum(is.na(reviews$`Food & Beverages`)), "missing data values in 'Food & Beverages' column.\n")

## There are 0 missing data values in 'Food & Beverages' column.

cat("There are", sum(is.na(reviews$`Inflight Entertainment`)), "missing data values in 'Inflight Entertainment' column.\n")

## There are 0 missing data values in 'Inflight Entertainment' column.

cat("There are", sum(is.na(reviews$`Ground Service`)), "missing data values in 'Ground Service' column.\n")

## There are 0 missing data values in 'Ground Service' column.

cat("There are", sum(is.na(reviews$`Wifi & Connectivity`)), "missing data values in 'Wifi & Connectivity' column.\n")

## There are 0 missing data values in 'Wifi & Connectivity' column.

cat("There are", sum(is.na(reviews$`Value For Money`)), "missing data values in 'Value for Money' column.\n")

## There are 0 missing data values in 'Value for Money' column.

cat("There are", sum(is.na(reviews$Reviews)), "missing data values in 'Reviews' column.\n")

## There are 0 missing data values in 'Reviews' column.

cat("There are", sum(is.na(reviews$Verification)), "missing data values in 'Verification' column.\n")

## There are 0 missing data values in 'Verification' column.

cat("There are", sum(is.na(reviews$Origin)), "missing data values in 'Origin' column.\n")

## There are 0 missing data values in 'Origin' column.

cat("There are", sum(is.na(reviews$Destination)), "missing data values in 'Destination' column.\n")

## There are 0 missing data values in 'Destination' column.

summary(reviews)

##  Type.Of.Traveller   Seat.Type          Date Flown        Recommended       
##  Length:1968        Length:1968        Length:1968        Length:1968       
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##   Seat Comfort   Cabin Staff Service Food & Beverages Inflight Entertainment
##  Min.   :1.000   Min.   :1.000       Min.   :1.000    Min.   :1.000         
##  1st Qu.:1.000   1st Qu.:1.000       1st Qu.:1.000    1st Qu.:1.000         
##  Median :2.000   Median :2.000       Median :2.000    Median :2.000         
##  Mean   :2.174   Mean   :2.173       Mean   :2.218    Mean   :2.181         
##  3rd Qu.:3.000   3rd Qu.:3.000       3rd Qu.:3.000    3rd Qu.:3.000         
##  Max.   :5.000   Max.   :5.000       Max.   :5.000    Max.   :5.000         
##  Ground Service  Wifi & Connectivity Value For Money   Reviews         
##  Min.   :1.000   Min.   :1.000       Min.   :1.000   Length:1968       
##  1st Qu.:1.000   1st Qu.:1.000       1st Qu.:1.000   Class :character  
##  Median :2.000   Median :2.000       Median :2.000   Mode  :character  
##  Mean   :2.148   Mean   :2.173       Mean   :2.177                     
##  3rd Qu.:3.000   3rd Qu.:3.000       3rd Qu.:3.000                     
##  Max.   :5.000   Max.   :5.000       Max.   :5.000                     
##   Total Rating   Verification          Origin          Final.Destination 
##  Min.   :1.000   Length:1968        Length:1968        Length:1968       
##  1st Qu.:1.714   Class :character   Class :character   Class :character  
##  Median :2.286   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :2.178                                                           
##  3rd Qu.:2.714                                                           
##  Max.   :3.429

dim(reviews)

## [1] 1968   16

Total_ratings_Business <- 0
for(i in 1:nrow(reviews)){
if(reviews$Type.Of.Traveller[i] == "Business"){
  Total_ratings_Business <- Total_ratings_Business + reviews$`Seat Comfort`[i] + reviews$`Cabin Staff Service`[i]+reviews$`Food & Beverages`[i] + reviews$`Inflight Entertainment`[i] + reviews$`Ground Service`[i] + reviews$`Wifi & Connectivity`[i] + reviews$`Value For Money`[i]
}}
Total_ratings_Business

## [1] 5915

Total_ratings_Couple <- 0
for(i in 1:nrow(reviews)){
if(reviews$Type.Of.Traveller[i] == "Couple Leisure"){
  Total_ratings_Couple <- Total_ratings_Couple + reviews$`Seat Comfort`[i] + reviews$`Cabin Staff Service`[i]+reviews$`Food & Beverages`[i] + reviews$`Inflight Entertainment`[i] + reviews$`Ground Service`[i] + reviews$`Wifi & Connectivity`[i] + reviews$`Value For Money`[i]
}}
Total_ratings_Couple

## [1] 6856

Total_ratings_Family <- 0
for(i in 1:nrow(reviews)){
if(reviews$Type.Of.Traveller[i] == "Family Leisure"){
  Total_ratings_Family <- Total_ratings_Family + reviews$`Seat Comfort`[i] + reviews$`Cabin Staff Service`[i]+reviews$`Food & Beverages`[i] + reviews$`Inflight Entertainment`[i] + reviews$`Ground Service`[i] + reviews$`Wifi & Connectivity`[i] + reviews$`Value For Money`[i]
}}
Total_ratings_Family

## [1] 7297

Total_ratings_Solo <- 0
for(i in 1:nrow(reviews)){
if(reviews$Type.Of.Traveller[i] == "Solo Leisure"){
  Total_ratings_Solo <- Total_ratings_Solo + reviews$`Seat Comfort`[i] + reviews$`Cabin Staff Service`[i]+reviews$`Food & Beverages`[i] + reviews$`Inflight Entertainment`[i] + reviews$`Ground Service`[i] + reviews$`Wifi & Connectivity`[i] + reviews$`Value For Money`[i]
}}
Total_ratings_Solo

## [1] 9933

#Word Cloud

# install.packages("wordcloud")
# library(wordcloud)
# install.packages("RColorBrewer")
# library(RColorBrewer)
# install.packages("tm")
# library(tm)
# install.packages("openNLP")
# install.packages("rJava")
# #library(openNLP)
# install.packages("NLP")
# library(NLP)
# 
# # Define a function to extract only adjectives from the text data
# adj_extractor <- function(text) {
#   word_tokenizer <- Maxent_Word_Token_Annotator()
#   pos_tag_annotator <- Maxent_POS_Tag_Annotator()
#   text <- as.String(text)
#   annotations <- NLP::annotate(text, list(word_tokenizer, pos_tag_annotator))
#   adjectives <- subset(annotations$POS, Type == "JJ")
#   adj_words <- text[adjectives]
#   return(adj_words)
# }
# 
# # Apply the adjective extractor to the text data
# text_data <- reviews$Reviews
# text_data <- gsub("flights", "", text_data)
# text_data <- gsub("plane", "", text_data)
# text_data <- gsub("airport", "", text_data)
# text_data <- gsub("get", "", text_data)
# text_data <- gsub("airline", "", text_data)
# text_data <- gsub("airlines", "", text_data)
# text_data <- gsub("flight", "", text_data)
# 
# adj_text_data <- sapply(text_data, adj_extractor)
# adj_text_data <- unlist(adj_text_data)
# adj_text_data <- gsub("[^[:alnum:][:space:]]*", "", adj_text_data)
# 
# docs <- Corpus(VectorSource(adj_text_data))
# 
# docs <- docs %>%
#   tm_map(removeNumbers) %>%
#   tm_map(removePunctuation) %>%
#   tm_map(stripWhitespace)
# 
# dtm <- TermDocumentMatrix(docs)
# matrix <- as.matrix(dtm)
# words <- sort(rowSums(matrix), decreasing=TRUE)
# df <- data.frame(word = names(words), freq = words)
# 
# set.seed(1234)
# wordcloud(
#   words = df$word,
#   freq = df$freq,
#   min.freq = 1,
#   max.words = 200,
#   random.order = FALSE,
#   rot.per = 0.35,
#   colors = brewer.pal(8, "Dark2")
# )

#install.packages("wordcloud")
library(wordcloud)

## Loading required package: RColorBrewer

#install.packages("RColorBrewer")
library(RColorBrewer)
#install.packages("tm")
library(tm)

## Loading required package: NLP

## 
## Attaching package: 'NLP'

## The following object is masked from 'package:ggplot2':
## 
##     annotate

text_data <- reviews$Reviews
text_data <- gsub("flights","",text_data)
text_data <- gsub("plane", "", text_data)
text_data <- gsub("airport", "", text_data)
text_data <- gsub("get","", text_data)
text_data <- gsub("airline", "", text_data)
text_data <- gsub("airlines","", text_data)
text_data <- gsub("flight", "", text_data)
docs <- Corpus(VectorSource(text_data))


docs <- docs %>%
  tm_map(removeNumbers) %>%
  tm_map(removePunctuation) %>%
  tm_map(stripWhitespace)

## Warning in tm_map.SimpleCorpus(., removeNumbers): transformation drops
## documents

## Warning in tm_map.SimpleCorpus(., removePunctuation): transformation drops
## documents

## Warning in tm_map.SimpleCorpus(., stripWhitespace): transformation drops
## documents

docs <- tm_map(docs, content_transformer(tolower))

## Warning in tm_map.SimpleCorpus(docs, content_transformer(tolower)):
## transformation drops documents

docs <- tm_map(docs, removeWords, stopwords("english"))

## Warning in tm_map.SimpleCorpus(docs, removeWords, stopwords("english")):
## transformation drops documents

dtm <- TermDocumentMatrix(docs)
matrix <- as.matrix(dtm)
words <- sort(rowSums(matrix),decreasing=TRUE)
df <- data.frame(word = names(words),freq=words)

set.seed(1234)
wordcloud(words = df$word, freq = df$freq, min.freq = 1, max.words=200, random.order=FALSE, rot.per=0.35, colors=brewer.pal(8, "Dark2"))

library(ggplot2)
ggplot(reviews, aes(x = `Type.Of.Traveller`, y = `Total Rating`, col=`Type.Of.Traveller`)) +
   geom_col() +
   xlab("Type of Traveler") +
   ylab("Total Ratings") +
   ggtitle("By travel type")

library(ggplot2)
ggplot(reviews, aes(x = `Seat.Type`, y = `Total Rating`, col=`Seat.Type`)) +
 geom_col() +
  xlab("Seat Type") +
  ylab("Total Ratings") +
  ggtitle("By Seat type")

library(ggplot2)
ggplot(reviews, aes(x = `Verification`, y = `Total Rating`, col=`Total Rating`)) +
 geom_col() +
  xlab("Seat Type") +
  ylab("Total Ratings") +
  ggtitle("By Verification")

type_counts <- table(reviews$Type.Of.Traveller)
type_df <- data.frame(Type.Of.Traveller = names(type_counts),
count = as.numeric(type_counts))
ggplot(type_df, aes(x = "", y = count, fill = Type.Of.Traveller)) +
geom_bar(width = 1, stat = "identity") +
coord_polar("y", start = 0) +
scale_fill_discrete(name = "Type of traveller") +
ggtitle("Type of traveler distribution") +
theme(plot.title = element_text(hjust = 0.5),
axis.line.y = element_blank(),
axis.text.y = element_blank(),
axis.ticks.y = element_blank()) +
geom_text(aes(label = count), position = position_stack(vjust = 0.5))

library(ggplot2)
library(reshape2)

## 
## Attaching package: 'reshape2'

## The following object is masked from 'package:tidyr':
## 
##     smiths

corr_data <- cor(reviews[, c("Seat Comfort", "Cabin Staff Service", "Food & Beverages",
"Inflight Entertainment", "Ground Service", "Wifi & Connectivity")])

melted_corr <- melt(corr_data)
ggplot(melted_corr, aes(x = Var1, y = value, fill = Var2)) +
geom_col() +
scale_fill_discrete(name = "Amenities") +
theme_minimal() +
ggtitle("Correlation between Amenities") +
xlab("Amenities") +
ylab("Correlation") +
theme(plot.title = element_text(hjust = 0.5, size = 16, face = "bold"),
axis.title = element_text(size = 14),
axis.text.x = element_text(angle = 45, hjust = 1),
legend.title = element_text(size = 12),
legend.text = element_text(size = 12),
legend.position = "bottom")

library(ggplot2)

# create the plot
ggplot(reviews, aes(x = Verification, fill = Recommended)) +
  geom_bar() +
  scale_fill_discrete(name = "Recommended") +
  theme_minimal() +
  ggtitle("Verification vs Recommended") +
  xlab("Verification") +
  ylab("Count") +
  theme(plot.title = element_text(hjust = 0.5, size = 16, face = "bold"),
        axis.title = element_text(size = 14),
        axis.text.x = element_text(angle = 45, hjust = 1),
        legend.title = element_text(size = 12),
        legend.text = element_text(size = 12),
        legend.position = "bottom")

# # Create a box plot for Verification vs Total Ratings
reviews %>% ggplot(aes(Verification, `Total Rating`)) + geom_boxplot() + geom_point(alpha = 0.5, aes(size = `Total Rating`, color = reviews$`Type Of Traveler`))

#Correlation plot between ameneties
library(corrplot)

## corrplot 0.92 loaded

amenities_df <- reviews[, c(5:11)]
col <- colorRampPalette(c("Black", "lightblue", "lightgreen"))

corrplot(
  cor(amenities_df),
  method = "ellipse",
  col = col(500),
  addCoef.col = "black",
  tl.col = "black"
)

## Warning in ind1:ind2: numerical expression has 2 elements: only the first used

pairs(amenities_df, main = "Ameneties", pch = 21, bg = c("#CFB87C"))

library(ggplot2)
ggplot(reviews, aes(x = `Date Flown`, fill = Recommended)) +
geom_bar(position = "dodge") +
scale_fill_manual(values = c("yes" = "green", "no" = "red")) +
labs(x = "Date Flown", y = "Count", fill = "Recommendation")

# K-Means

# install.packages("factoextra")
# load required libraries
# Load required libraries
library(factoextra)

## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa

# Prerequisites
Reviews.Labels <- reviews$Type.Of.Traveller
table(Reviews.Labels)

## Reviews.Labels
##       Business Couple Leisure Family Leisure   Solo Leisure 
##            386            460            473            649

reviews_kmeans_clustering <- reviews[5:10]
head(reviews_kmeans_clustering)

##   Seat Comfort Cabin Staff Service Food & Beverages Inflight Entertainment
## 1            1                   2                3                      1
## 2            2                   3                1                      2
## 3            1                   2                3                      1
## 4            1                   2                3                      1
## 5            3                   1                1                      1
## 6            1                   1                1                      2
##   Ground Service Wifi & Connectivity
## 1              2                   3
## 2              3                   1
## 3              2                   1
## 4              1                   1
## 5              1                   1
## 6              3                   4

# Scale the data
reviews_kmeans_clustering_scale <- scale(reviews_kmeans_clustering)

# Calculate K for K-Means using Elbow Method and Silhouette Method
fviz_nbclust(reviews_kmeans_clustering_scale, kmeans, method = "wss") + geom_vline(xintercept = 4, linetype = 2) + labs(subtitle = "Elbow Method")

fviz_nbclust(reviews_kmeans_clustering_scale, kmeans, method = "silhouette") + labs(subtitle = "Silhouette Method")

# Calculate Distance
reviews.dist <- dist(reviews_kmeans_clustering_scale)

# Perform K-Means
km.out <- kmeans(reviews_kmeans_clustering_scale, centers = 4, nstart = 1000)
print(km.out)

## K-means clustering with 4 clusters of sizes 897, 231, 434, 406
## 
## Cluster means:
##   Seat Comfort Cabin Staff Service Food & Beverages Inflight Entertainment
## 1   -0.4127647         -0.50050225       -0.5482564             -0.5569192
## 2    0.3345114          1.12412374        1.8558250             -0.9156574
## 3    1.2273702          0.39093024       -0.5959371              0.1491683
## 4   -0.5903961          0.04831086        0.7924312              1.5919565
##   Ground Service Wifi & Connectivity
## 1     -0.5015258          -0.4017139
## 2     -0.2820461           0.2425646
## 3      0.8787580           1.2184140
## 4      0.3291632          -0.5529230
## 
## Clustering vector:
##    1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
##    1    1    1    1    1    1    1    1    1    2    1    3    1    1    4    1 
##   17   18   19   20   21   22   23   24   25   26   27   28   29   30   31   32 
##    2    1    1    1    1    1    3    2    4    4    3    1    3    2    3    4 
##   33   34   35   36   37   38   39   40   41   42   43   44   45   46   47   48 
##    1    1    1    1    1    1    3    1    3    4    1    1    1    1    1    1 
##   49   50   51   52   53   54   55   56   57   58   59   60   61   62   63   64 
##    1    1    1    4    2    4    2    3    1    1    3    4    3    3    1    1 
##   65   66   67   68   69   70   71   72   73   74   75   76   77   78   79   80 
##    1    2    3    4    3    4    1    2    1    1    3    4    3    4    2    4 
##   81   82   83   84   85   86   87   88   89   90   91   92   93   94   95   96 
##    2    3    4    1    1    1    1    1    3    4    3    1    2    1    2    1 
##   97   98   99  100  101  102  103  104  105  106  107  108  109  110  111  112 
##    1    3    1    1    1    1    1    1    1    1    3    4    3    4    3    2 
##  113  114  115  116  117  118  119  120  121  122  123  124  125  126  127  128 
##    4    3    4    3    1    1    1    1    1    2    3    4    2    2    3    2 
##  129  130  131  132  133  134  135  136  137  138  139  140  141  142  143  144 
##    3    1    3    3    4    3    4    3    3    4    2    1    4    2    3    1 
##  145  146  147  148  149  150  151  152  153  154  155  156  157  158  159  160 
##    3    1    1    1    1    1    2    3    4    3    4    4    3    1    3    1 
##  161  162  163  164  165  166  167  168  169  170  171  172  173  174  175  176 
##    1    1    3    4    3    2    1    1    3    4    3    4    2    1    1    1 
##  177  178  179  180  181  182  183  184  185  186  187  188  189  191  192  193 
##    1    1    1    1    1    4    1    1    1    1    4    3    1    1    1    1 
##  194  195  196  197  198  199  200  201  202  203  204  205  206  207  208  209 
##    1    1    1    1    3    4    2    3    2    1    1    1    1    4    1    3 
##  210  211  212  213  214  215  216  217  218  219  220  221  222  223  224  225 
##    1    4    1    1    3    1    3    4    3    1    1    4    3    4    3    4 
##  226  227  228  229  230  231  232  233  234  235  236  237  238  240  241  242 
##    1    4    4    3    2    3    4    3    4    2    4    2    3    1    3    1 
##  243  244  245  246  247  248  249  250  251  252  253  254  255  256  257  258 
##    3    1    4    3    4    3    4    3    3    2    1    1    1    1    4    3 
##  259  260  261  262  263  264  265  266  267  268  269  270  271  272  273  274 
##    3    4    3    2    3    4    1    1    3    4    2    3    4    1    1    1 
##  275  276  277  278  279  280  281  282  283  284  285  286  287  288  289  290 
##    1    3    4    3    4    1    1    1    3    2    2    1    1    4    4    3 
##  291  292  293  294  295  296  297  298  299  300  301  302  303  304  305  306 
##    4    3    1    4    2    3    4    3    3    3    1    1    4    4    1    1 
##  307  308  309  310  311  312  313  314  315  316  317  318  319  320  321  322 
##    1    1    1    4    3    4    2    3    4    2    1    3    4    3    3    1 
##  323  324  325  326  327  328  329  330  331  332  333  334  335  336  337  338 
##    3    1    1    1    1    1    3    3    3    4    2    3    4    2    4    1 
##  339  340  341  342  343  344  345  346  347  348  349  350  351  352  353  354 
##    1    1    4    4    1    3    4    2    3    2    1    1    1    4    1    1 
##  355  356  357  358  359  360  361  362  363  364  365  366  367  368  369  370 
##    1    4    1    1    3    3    4    1    1    2    1    1    1    1    1    3 
##  371  372  373  374  375  376  377  378  379  380  382  383  384  385  386  387 
##    1    1    1    1    4    3    3    4    1    1    1    1    4    3    4    2 
##  388  389  390  391  392  393  394  395  396  397  398  399  400  401  402  403 
##    1    3    1    4    3    4    2    3    4    4    2    3    2    4    4    1 
##  404  405  406  407  408  409  410  411  412  413  414  415  416  417  418  419 
##    3    1    1    1    1    4    1    1    3    2    4    3    4    2    3    4 
##  420  421  422  423  424  425  426  427  428  429  430  431  432  433  434  435 
##    4    4    1    1    1    2    1    1    1    1    2    3    4    3    4    3 
##  436  437  439  440  441  442  443  444  445  446  447  448  449  450  451  452 
##    4    1    1    3    1    1    3    2    3    3    1    4    2    1    4    3 
##  453  454  455  456  457  458  459  460  461  462  463  464  465  466  467  468 
##    4    2    3    1    1    1    1    1    1    1    1    1    1    3    2    1 
##  469  470  471  472  473  474  475  477  478  479  480  481  482  483  484  485 
##    3    4    3    3    1    1    3    2    1    4    3    4    2    3    1    1 
##  486  487  488  489  490  491  492  493  494  495  496  497  498  499  500  501 
##    1    1    2    3    1    3    2    3    4    1    1    3    1    1    1    1 
##  502  503  504  505  506  507  508  509  510  511  512  513  514  515  516  517 
##    3    1    1    1    4    1    1    2    4    3    2    3    1    3    4    2 
##  518  519  520  521  522  523  524  525  527  528  529  530  531  532  533  534 
##    4    3    1    1    1    1    3    4    3    2    4    1    4    3    4    3 
##  535  536  537  538  539  540  541  542  543  544  545  546  547  548  549  550 
##    3    4    3    4    1    1    1    1    1    4    3    4    2    3    1    4 
##  551  552  553  554  555  556  557  558  559  560  561  562  563  564  565  567 
##    2    4    1    4    2    2    2    4    2    3    1    1    3    4    2    1 
##  568  569  570  571  572  573  574  575  576  577  578  579  580  581  582  583 
##    4    3    1    3    1    1    3    4    2    3    4    3    1    1    1    1 
##  584  585  586  587  588  589  590  591  592  593  594  595  596  597  598  599 
##    2    1    2    3    4    3    4    2    3    4    3    1    1    1    3    1 
##  600  601  602  603  604  605  606  607  608  609  610  611  612  613  614  615 
##    1    1    4    4    3    4    1    1    1    1    1    1    1    1    4    1 
##  616  617  618  619  620  621  622  623  624  625  626  627  628  629  630  631 
##    1    1    3    4    2    3    4    4    1    1    1    1    1    1    3    3 
##  632  633  634  635  636  637  638  639  640  641  642  643  644  645  646  647 
##    4    4    2    4    4    1    1    4    3    4    2    1    1    1    2    3 
##  648  649  650  651  652  653  655  656  657  658  659  660  661  662  663  664 
##    4    3    1    1    1    1    2    1    2    3    3    4    1    1    1    4 
##  665  666  667  668  669  670  671  672  673  674  675  677  678  679  680  681 
##    3    4    2    1    1    1    1    3    2    1    2    4    3    4    1    1 
##  682  683  684  685  686  688  689  690  691  692  693  694  695  696  697  698 
##    1    1    3    4    3    1    3    1    1    1    1    1    1    1    3    2 
##  699  700  701  702  703  704  705  706  707  708  709  710  711  712  713  714 
##    1    1    1    1    1    1    1    3    4    4    1    3    1    1    1    1 
##  715  716  717  718  719  720  721  722  723  724  725  726  727  728  729  730 
##    1    3    1    1    1    1    1    1    1    1    1    1    1    1    1    1 
##  731  732  733  734  735  736  737  738  739  740  741  742  743  744  745  746 
##    1    1    1    1    1    1    1    1    3    1    2    3    1    1    1    4 
##  747  748  749  750  751  752  753  754  755  756  757  758  759  760  761  762 
##    2    1    1    4    3    1    1    1    1    1    4    3    4    2    3    1 
##  763  764  765  766  767  768  769  770  771  772  773  774  775  776  777  778 
##    1    1    1    1    1    1    1    1    4    1    1    2    3    4    3    4 
##  779  780  781  782  783  784  785  786  787  788  789  790  791  792  793  794 
##    2    1    1    1    1    2    1    1    1    1    2    4    1    1    1    2 
##  795  796  797  798  799  800  801  802  803  804  805  806  807  808  809  810 
##    4    3    3    1    1    1    4    3    3    4    1    1    1    1    2    3 
##  811  812  813  814  815  816  817  818  819  820  821  822  823  824  825  826 
##    3    2    2    3    4    3    4    1    1    1    4    1    4    1    3    2 
##  827  828  829  830  831  832  833  834  835  836  837  838  839  840  841  842 
##    4    1    1    1    3    3    1    1    4    3    1    2    1    4    2    1 
##  843  844  845  846  847  848  849  850  851  852  853  854  855  856  857  858 
##    3    4    3    4    2    1    1    1    4    2    1    3    2    3    1    4 
##  859  860  861  862  863  864  865  866  867  868  869  870  871  872  873  874 
##    1    1    1    1    1    3    1    1    1    2    4    3    4    1    2    4 
##  875  876  877  878  879  880  881  882  883  884  885  886  887  888  889  890 
##    1    1    2    4    1    1    2    3    2    3    4    1    1    1    1    2 
##  891  892  893  894  895  896  897  898  899  900  901  902  903  904  905  906 
##    3    3    2    1    3    4    3    4    3    4    2    3    4    3    4    1 
##  907  908  909  910  911  912  913  914  915  916  917  918  919  920  921  922 
##    1    2    3    1    1    1    1    4    2    3    3    1    1    1    3    4 
##  923  924  925  926  927  928  929  930  931  932  933  934  935  936  937  938 
##    2    1    1    2    1    1    1    1    1    1    1    1    1    1    1    1 
##  939  940  941  942  943  944  945  946  947  948  949  950  951  952  953  954 
##    1    3    4    3    4    3    1    1    1    1    1    1    3    2    1    1 
##  955  956  957  958  959  960  961  962  963  964  965  966  967  968  969  970 
##    3    1    1    1    1    1    1    1    1    1    1    1    1    4    4    2 
##  971  972  973  974  975  976  977  978  979  980  981  982  983  984  985  986 
##    1    1    1    1    1    1    3    2    3    2    1    2    4    2    4    3 
##  987  988  989  990  991  992  993  994  995  996  997  998  999 1000 1001 1002 
##    1    1    4    3    1    1    1    3    4    4    1    1    4    3    4    1 
## 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 
##    1    1    1    1    1    2    3    3    3    4    3    4    3    1    1    1 
## 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 
##    1    1    1    1    1    1    3    2    4    3    4    2    3    4    1    3 
## 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 
##    3    4    3    1    1    1    1    1    1    3    1    1    1    2    2    1 
## 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 
##    1    1    1    1    1    1    1    2    1    3    4    2    3    1    3    4 
## 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 
##    3    1    1    1    2    1    1    1    1    1    3    1    1    1    1    4 
## 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 
##    1    1    1    1    1    1    1    4    1    3    4    3    2    3    2    3 
## 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 
##    4    3    2    4    1    4    1    1    1    1    1    1    1    3    4    2 
## 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 
##    4    4    2    2    1    1    1    1    2    1    1    3    2    1    1    2 
## 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 
##    1    2    4    4    4    4    1    3    4    3    4    3    1    1    1    1 
## 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 
##    3    4    3    2    3    1    2    2    1    1    4    3    4    2    1    3 
## 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 
##    3    4    4    4    1    1    1    4    2    3    4    1    4    1    1    4 
## 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 
##    1    1    2    3    3    1    1    3    3    4    3    2    3    4    3    4 
## 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 
##    2    3    4    3    1    1    1    1    3    1    1    3    1    2    4    4 
## 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 
##    1    1    1    4    2    3    4    3    1    3    2    1    1    1    2    3 
## 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 
##    4    3    4    1    1    2    3    3    4    3    2    3    4    1    3    1 
## 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 
##    3    3    1    1    1    1    4    1    2    1    1    1    4    3    4    2 
## 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 
##    3    1    1    1    4    4    3    4    2    2    4    1    4    1    4    3 
## 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 
##    1    2    4    1    1    1    3    1    3    2    1    1    1    1    1    1 
## 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 
##    1    1    1    1    1    1    1    3    1    3    1    3    2    4    1    1 
## 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 
##    1    1    4    1    3    3    4    1    1    1    3    1    1    1    1    4 
## 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1338 1339 
##    1    1    1    1    4    1    4    1    1    1    1    1    1    1    3    4 
## 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 
##    3    4    4    4    4    1    1    1    1    1    1    1    1    3    1    4 
## 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 
##    4    1    1    4    3    1    1    1    1    1    1    1    1    1    1    1 
## 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 
##    4    1    1    3    1    3    1    1    1    2    1    1    1    1    4    2 
## 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 
##    4    1    3    1    1    1    1    2    4    3    1    1    1    1    2    4 
## 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 
##    3    4    2    4    1    1    1    1    4    1    1    3    1    2    1    3 
## 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 
##    4    2    1    1    1    1    4    4    1    1    1    2    1    1    4    1 
## 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 
##    2    3    4    1    1    4    3    4    3    1    2    4    1    2    3    4 
## 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 
##    1    1    1    1    1    4    1    1    1    1    1    3    1    1    1    1 
## 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 
##    2    1    1    1    2    3    4    3    1    1    4    1    1    1    1    4 
## 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 
##    3    4    2    1    1    1    1    1    2    3    4    3    1    1    4    3 
## 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 
##    4    3    4    3    4    3    4    3    3    3    2    3    3    4    1    1 
## 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 
##    3    2    3    4    3    3    4    1    1    1    1    1    1    1    3    1 
## 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 
##    1    1    1    4    1    1    1    2    3    1    1    1    1    3    3    4 
## 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 
##    1    3    4    3    4    3    4    1    1    3    4    3    2    3    4    3 
## 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 
##    4    2    1    1    1    1    4    1    3    1    2    1    3    4    3    4 
## 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 
##    2    1    1    1    4    2    2    2    3    4    3    4    3    1    2    3 
## 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 
##    1    4    3    1    1    1    1    1    4    1    3    2    3    4    4    2 
## 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 
##    4    3    3    1    3    4    2    3    4    3    4    2    3    4    3    1 
## 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 
##    1    1    4    2    1    3    3    4    1    4    2    4    3    1    1    3 
## 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 
##    3    4    1    2    3    4    3    2    1    4    1    3    4    4    1    1 
## 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 
##    2    3    2    1    1    4    4    1    1    1    1    1    1    1    4    2 
## 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 
##    4    4    4    3    1    4    2    1    3    4    3    1    1    1    4    2 
## 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 
##    3    4    4    2    1    3    1    3    3    1    3    4    3    1    1    4 
## 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 
##    3    2    1    2    1    1    3    1    4    3    4    1    3    2    4    4 
## 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 
##    1    3    3    4    1    4    3    3    4    1    1    1    1    1    1    3 
## 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1753 1754 1755 1756 
##    4    4    2    3    2    3    4    1    1    1    1    1    4    3    4    3 
## 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 
##    4    3    1    3    1    1    1    1    4    3    2    4    1    1    2    3 
## 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 
##    4    4    3    4    2    1    1    4    4    1    3    4    2    3    4    1 
## 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 
##    3    4    1    4    1    1    1    1    1    1    2    1    1    1    1    1 
## 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 
##    1    1    1    2    4    3    2    2    1    1    1    4    2    3    4    2 
## 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 
##    3    1    4    3    2    3    1    4    1    1    1    1    1    1    1    3 
## 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 
##    4    3    3    4    2    3    4    3    4    2    1    1    1    1    4    3 
## 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 
##    4    2    2    3    4    4    1    1    1    1    3    3    3    4    3    4 
## 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 
##    2    3    4    3    4    2    3    4    3    4    1    2    1    3    4    2 
## 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 
##    4    4    4    3    3    4    2    3    4    3    1    3    4    1    1    4 
## 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 
##    3    4    3    4    2    4    3    1    3    3    2    3    4    3    4    2 
## 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 
##    4    1    1    3    1    4    1    3    1    1    2    3    4    2    3    3 
## 1933 1934 1935 1936 1937 1938 1939 1940 1942 1943 1944 1945 1946 1947 1948 1949 
##    4    3    4    2    1    3    4    3    1    3    4    2    1    1    1    4 
## 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 
##    1    1    1    1    4    2    3    4    1    1    1    1    1    1    1    1 
## 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1977 1978 1979 1980 1981 1982 
##    1    1    1    4    3    4    2    3    3    4    3    4    2    3    4    2 
## 
## Within cluster sum of squares by cluster:
## [1] 2148.4354  225.1447 2014.8653 1321.0365
##  (between_SS / total_SS =  51.6 %)
## 
## Available components:
## 
## [1] "cluster"      "centers"      "totss"        "withinss"     "tot.withinss"
## [6] "betweenss"    "size"         "iter"         "ifault"

# 51.6 % classification or identification of an observation with a group - could be better.

# Creating a new dataframe to assign the values of Type of Traveler
reviews_tot <- reviews[1]
names(reviews_tot) <- c("Type.Of.Traveler")
reviews_tot$Type.Of.Traveler <- substr(reviews_tot$Type.Of.Traveler, 1, 1)

rownames(reviews_kmeans_clustering_scale) <- paste(reviews_tot$Type.Of.Traveler, 1:dim(reviews_tot)[1], sep = "_")      

head(reviews_kmeans_clustering_scale)

##     Seat Comfort Cabin Staff Service Food & Beverages Inflight Entertainment
## B_1   -0.9268708          -0.1363212        0.6099306             -0.9156574
## S_2   -0.1372250           0.6527378       -0.9499698             -0.1402642
## C_3   -0.9268708          -0.1363212        0.6099306             -0.9156574
## C_4   -0.9268708          -0.1363212        0.6099306             -0.9156574
## S_5    0.6524207          -0.9253802       -0.9499698             -0.9156574
## F_6   -0.9268708          -0.9253802       -0.9499698             -0.1402642
##     Ground Service Wifi & Connectivity
## B_1     -0.1174966           0.6526826
## S_2      0.6743981          -0.9262718
## C_3     -0.1174966          -0.9262718
## C_4     -0.9093913          -0.9262718
## S_5     -0.9093913          -0.9262718
## F_6      0.6743981           1.4421598

km.out <- kmeans(reviews_kmeans_clustering_scale, centers = 3, nstart = 100)

km.clusters <- km.out$clusters

p1 <- fviz_cluster(list(data=reviews_kmeans_clustering_scale, cluster = km.out$cluster)) + ggtitle("k=3")

km.out <- kmeans(reviews_kmeans_clustering_scale, centers = 4, nstart = 100)

km.clusters <- km.out$clusters

p2 <- fviz_cluster(list(data=reviews_kmeans_clustering_scale, cluster = km.out$cluster)) + ggtitle("k=4")

km.out <- kmeans(reviews_kmeans_clustering_scale, centers = 7, nstart = 100)

km.clusters <- km.out$clusters

p3 <- fviz_cluster(list(data=reviews_kmeans_clustering_scale, cluster = km.out$cluster)) + ggtitle("k=7")

km.out <- kmeans(reviews_kmeans_clustering_scale, centers = 8, nstart = 100)

km.clusters <- km.out$clusters

p4 <- fviz_cluster(list(data=reviews_kmeans_clustering_scale, cluster = km.out$cluster)) + ggtitle("k=8")

library(gridExtra)

## 
## Attaching package: 'gridExtra'

## The following object is masked from 'package:dplyr':
## 
##     combine

grid.arrange(p1,p2,p3,p4, nrow=2)

Hierarchical Clustering

# Prerequisites
Reviews.Labels <- reviews$Type.Of.Traveller
table(Reviews.Labels)

## Reviews.Labels
##       Business Couple Leisure Family Leisure   Solo Leisure 
##            386            460            473            649

reviews_hierarchical_clustering <- reviews[5:11]

# Scale the data
reviews_hierarchical_clustering_scale <- scale(reviews_hierarchical_clustering)

# Distance Calculating using Cosine Similarity
cosine_matrix <- as.matrix(reviews_hierarchical_clustering_scale)
reviews_cosine_distance <- 1 - crossprod(cosine_matrix) / sqrt(colSums(cosine_matrix^2) %*% t(colSums(cosine_matrix^2)))
hc.out_reviews <- hclust(as.dist(reviews_cosine_distance), method = "ward.D")
# hc.out_reviews
hierarchical.dist <- as.dist(reviews_cosine_distance)

# Dendogram
hc.out_reviews <- hclust(hierarchical.dist, method = "ward.D")
plot(hc.out_reviews)
rect.hclust(hc.out_reviews, k=3, border = 2:5)

Association Rule Mining

#install.packages("arules")
#install.packages("arulesViz")
library(arules)

## Loading required package: Matrix

## 
## Attaching package: 'Matrix'

## The following objects are masked from 'package:tidyr':
## 
##     expand, pack, unpack

## 
## Attaching package: 'arules'

## The following object is masked from 'package:tm':
## 
##     inspect

## The following object is masked from 'package:dplyr':
## 
##     recode

## The following objects are masked from 'package:base':
## 
##     abbreviate, write

library(arulesViz)

reviews_apriori <- reviews[, c(1,2,4,13)]
summary(reviews_apriori)

##  Type.Of.Traveller   Seat.Type         Recommended         Total Rating  
##  Length:1968        Length:1968        Length:1968        Min.   :1.000  
##  Class :character   Class :character   Class :character   1st Qu.:1.714  
##  Mode  :character   Mode  :character   Mode  :character   Median :2.286  
##                                                           Mean   :2.178  
##                                                           3rd Qu.:2.714  
##                                                           Max.   :3.429

rule1 <- apriori(reviews_apriori, parameter=list(suppor = 0.002, confidence = 0.5)) 

## Warning: Column(s) 1, 2, 3, 4 not logical or factor. Applying default
## discretization (see '? discretizeDF').

## Apriori
## 
## Parameter specification:
##  confidence minval smax arem  aval originalSupport maxtime support minlen
##         0.5    0.1    1 none FALSE            TRUE       5   0.002      1
##  maxlen target  ext
##      10  rules TRUE
## 
## Algorithmic control:
##  filter tree heap memopt load sort verbose
##     0.1 TRUE TRUE  FALSE TRUE    2    TRUE
## 
## Absolute minimum support count: 3 
## 
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[13 item(s), 1968 transaction(s)] done [0.00s].
## sorting and recoding items ... [13 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 done [0.00s].
## writing ... [167 rule(s)] done [0.00s].
## creating S4 object  ... done [0.00s].

inspect(head(sort(rule1, by = "lift"), 20))

##      lhs                                    rhs                                  support confidence    coverage     lift count
## [1]  {Type.Of.Traveller=Family Leisure,                                                                                       
##       Seat.Type=Business Class,                                                                                               
##       Total Rating=[2.57,3.43]}          => {Recommended=yes}                0.003048780  1.0000000 0.003048780 3.352641     6
## [2]  {Type.Of.Traveller=Solo Leisure,                                                                                         
##       Seat.Type=First Class,                                                                                                  
##       Total Rating=[2.57,3.43]}          => {Recommended=yes}                0.006097561  0.6315789 0.009654472 2.117457    12
## [3]  {Type.Of.Traveller=Family Leisure,                                                                                       
##       Seat.Type=Business Class,                                                                                               
##       Recommended=yes}                   => {Total Rating=[2.57,3.43]}       0.003048780  0.7500000 0.004065041 2.058577     6
## [4]  {Type.Of.Traveller=Solo Leisure,                                                                                         
##       Seat.Type=Premium Economy,                                                                                              
##       Total Rating=[1,1.86)}             => {Recommended=yes}                0.003048780  0.6000000 0.005081301 2.011584     6
## [5]  {Type.Of.Traveller=Family Leisure,                                                                                       
##       Seat.Type=Business Class,                                                                                               
##       Recommended=no}                    => {Total Rating=[1,1.86)}          0.002032520  0.5714286 0.003556911 1.955776     4
## [6]  {Type.Of.Traveller=Business,                                                                                             
##       Seat.Type=Business Class,                                                                                               
##       Total Rating=[1,1.86)}             => {Recommended=yes}                0.002032520  0.5714286 0.003556911 1.915795     4
## [7]  {Type.Of.Traveller=Family Leisure,                                                                                       
##       Seat.Type=First Class,                                                                                                  
##       Recommended=yes}                   => {Total Rating=[2.57,3.43]}       0.002032520  0.6666667 0.003048780 1.829847     4
## [8]  {Type.Of.Traveller=Couple Leisure,                                                                                       
##       Seat.Type=Premium Economy,                                                                                              
##       Total Rating=[1,1.86)}             => {Recommended=yes}                0.003556911  0.5384615 0.006605691 1.805268     7
## [9]  {Type.Of.Traveller=Family Leisure,                                                                                       
##       Seat.Type=Business Class}          => {Recommended=yes}                0.004065041  0.5333333 0.007621951 1.788075     8
## [10] {Type.Of.Traveller=Solo Leisure,                                                                                         
##       Seat.Type=First Class}             => {Recommended=yes}                0.010670732  0.5121951 0.020833333 1.717206    21
## [11] {Type.Of.Traveller=Family Leisure,                                                                                       
##       Seat.Type=First Class,                                                                                                  
##       Total Rating=[2.57,3.43]}          => {Recommended=yes}                0.002032520  0.5000000 0.004065041 1.676320     4
## [12] {Type.Of.Traveller=Solo Leisure,                                                                                         
##       Seat.Type=First Class,                                                                                                  
##       Total Rating=[1,1.86)}             => {Recommended=yes}                0.002540650  0.5000000 0.005081301 1.676320     5
## [13] {Type.Of.Traveller=Solo Leisure,                                                                                         
##       Seat.Type=Premium Economy,                                                                                              
##       Recommended=yes}                   => {Total Rating=[1.86,2.57)}       0.004573171  0.5625000 0.008130081 1.637574     9
## [14] {Type.Of.Traveller=Solo Leisure,                                                                                         
##       Seat.Type=First Class,                                                                                                  
##       Recommended=yes}                   => {Total Rating=[2.57,3.43]}       0.006097561  0.5714286 0.010670732 1.568440    12
## [15] {Seat.Type=First Class,                                                                                                  
##       Recommended=yes,                                                                                                        
##       Total Rating=[2.57,3.43]}          => {Type.Of.Traveller=Solo Leisure} 0.006097561  0.5000000 0.012195122 1.516179    12
## [16] {Type.Of.Traveller=Family Leisure,                                                                                       
##       Seat.Type=Business Class,                                                                                               
##       Total Rating=[1,1.86)}             => {Recommended=no}                 0.002032520  1.0000000 0.002032520 1.425054     4
## [17] {Type.Of.Traveller=Family Leisure,                                                                                       
##       Seat.Type=First Class,                                                                                                  
##       Total Rating=[1,1.86)}             => {Recommended=no}                 0.004065041  1.0000000 0.004065041 1.425054     8
## [18] {Type.Of.Traveller=Solo Leisure,                                                                                         
##       Seat.Type=Premium Economy,                                                                                              
##       Recommended=no}                    => {Total Rating=[2.57,3.43]}       0.007621951  0.5172414 0.014735772 1.419709    15
## [19] {Type.Of.Traveller=Solo Leisure,                                                                                         
##       Seat.Type=Premium Economy,                                                                                              
##       Total Rating=[2.57,3.43]}          => {Recommended=no}                 0.007621951  0.9375000 0.008130081 1.335988    15
## [20] {Type.Of.Traveller=Family Leisure,                                                                                       
##       Recommended=yes,                                                                                                        
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class}        0.014227642  0.9655172 0.014735772 1.241109    28

plot(rule1)

## To reduce overplotting, jitter is added! Use jitter = 0 to prevent jitter.

plot(rule1, method = "grouped")

inspect(head(sort(rule1, by = "confidence"), 20))

##      lhs                                    rhs                           support confidence    coverage     lift count
## [1]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Seat.Type=Business Class,                                                                                        
##       Total Rating=[1,1.86)}             => {Recommended=no}          0.002032520  1.0000000 0.002032520 1.425054     4
## [2]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Seat.Type=Business Class,                                                                                        
##       Total Rating=[2.57,3.43]}          => {Recommended=yes}         0.003048780  1.0000000 0.003048780 3.352641     6
## [3]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Seat.Type=First Class,                                                                                           
##       Total Rating=[1,1.86)}             => {Recommended=no}          0.004065041  1.0000000 0.004065041 1.425054     8
## [4]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=yes,                                                                                                 
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.014227642  0.9655172 0.014735772 1.241109    28
## [5]  {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Seat.Type=Premium Economy,                                                                                       
##       Total Rating=[2.57,3.43]}          => {Recommended=no}          0.007621951  0.9375000 0.008130081 1.335988    15
## [6]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[2.57,3.43]}          => {Seat.Type=Economy Class} 0.057926829  0.8837209 0.065548780 1.135965   114
## [7]  {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.060467480  0.8686131 0.069613821 1.116545   119
## [8]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.056910569  0.8682171 0.065548780 1.116036   112
## [9]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.055386179  0.8650794 0.064024390 1.112003   109
## [10] {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no}                    => {Seat.Type=Economy Class} 0.155995935  0.8647887 0.180386179 1.111629   307
## [11] {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.071646341  0.8545455 0.083841463 1.098462   141
## [12] {Type.Of.Traveller=Family Leisure}  => {Seat.Type=Economy Class} 0.205284553  0.8541226 0.240345528 1.097919   404
## [13] {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[2.57,3.43]}          => {Seat.Type=Economy Class} 0.078252033  0.8461538 0.092479675 1.087675   154
## [14] {Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.170731707  0.8358209 0.204268293 1.074393   336
## [15] {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.041158537  0.8350515 0.049288618 1.073404    81
## [16] {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.085365854  0.8316832 0.102642276 1.069074   168
## [17] {Type.Of.Traveller=Couple Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.042174797  0.8300000 0.050813008 1.066911    83
## [18] {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Recommended=no}                    => {Seat.Type=Economy Class} 0.182926829  0.8275862 0.221036585 1.063808   360
## [19] {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Recommended=no,                                                                                                  
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.057926829  0.8260870 0.070121951 1.061881   114
## [20] {Type.Of.Traveller=Couple Leisure,                                                                                
##       Seat.Type=First Class,                                                                                           
##       Total Rating=[2.57,3.43]}          => {Recommended=no}          0.007113821  0.8235294 0.008638211 1.173574    14

inspect(head(sort(rule1, by = "support"), 20))

##      lhs                                   rhs                         support confidence  coverage      lift count
## [1]  {}                                 => {Seat.Type=Economy Class} 0.7779472  0.7779472 1.0000000 1.0000000  1531
## [2]  {}                                 => {Recommended=no}          0.7017276  0.7017276 1.0000000 1.0000000  1381
## [3]  {Recommended=no}                   => {Seat.Type=Economy Class} 0.5579268  0.7950760 0.7017276 1.0220180  1098
## [4]  {Seat.Type=Economy Class}          => {Recommended=no}          0.5579268  0.7171783 0.7779472 1.0220180  1098
## [5]  {Total Rating=[2.57,3.43]}         => {Seat.Type=Economy Class} 0.2799797  0.7684798 0.3643293 0.9878303   551
## [6]  {Type.Of.Traveller=Solo Leisure}   => {Seat.Type=Economy Class} 0.2652439  0.8043143 0.3297764 1.0338933   522
## [7]  {Total Rating=[1.86,2.57)}         => {Seat.Type=Economy Class} 0.2616870  0.7618343 0.3434959 0.9792880   515
## [8]  {Total Rating=[2.57,3.43]}         => {Recommended=no}          0.2535569  0.6959554 0.3643293 0.9917742   499
## [9]  {Total Rating=[1.86,2.57)}         => {Recommended=no}          0.2439024  0.7100592 0.3434959 1.0118729   480
## [10] {Total Rating=[1,1.86)}            => {Seat.Type=Economy Class} 0.2362805  0.8086957 0.2921748 1.0395252   465
## [11] {Type.Of.Traveller=Solo Leisure}   => {Recommended=no}          0.2210366  0.6702619 0.3297764 0.9551597   435
## [12] {Recommended=yes}                  => {Seat.Type=Economy Class} 0.2200203  0.7376491 0.2982724 0.9481994   433
## [13] {Type.Of.Traveller=Family Leisure} => {Seat.Type=Economy Class} 0.2052846  0.8541226 0.2403455 1.0979186   404
## [14] {Total Rating=[1,1.86)}            => {Recommended=no}          0.2042683  0.6991304 0.2921748 0.9962988   402
## [15] {Recommended=no,                                                                                              
##       Total Rating=[2.57,3.43]}         => {Seat.Type=Economy Class} 0.1986789  0.7835671 0.2535569 1.0072241   391
## [16] {Seat.Type=Economy Class,                                                                                     
##       Total Rating=[2.57,3.43]}         => {Recommended=no}          0.1986789  0.7096189 0.2799797 1.0112454   391
## [17] {Recommended=no,                                                                                              
##       Total Rating=[1.86,2.57)}         => {Seat.Type=Economy Class} 0.1885163  0.7729167 0.2439024 0.9935336   371
## [18] {Seat.Type=Economy Class,                                                                                     
##       Total Rating=[1.86,2.57)}         => {Recommended=no}          0.1885163  0.7203883 0.2616870 1.0265925   371
## [19] {Type.Of.Traveller=Solo Leisure,                                                                              
##       Recommended=no}                   => {Seat.Type=Economy Class} 0.1829268  0.8275862 0.2210366 1.0638077   360
## [20] {Type.Of.Traveller=Solo Leisure,                                                                              
##       Seat.Type=Economy Class}          => {Recommended=no}          0.1829268  0.6896552 0.2652439 0.9827961   360

rule2 <- apriori(reviews_apriori, parameter=list(suppor = 0.005, confidence = 0.75)) 

## Warning: Column(s) 1, 2, 3, 4 not logical or factor. Applying default
## discretization (see '? discretizeDF').

## Apriori
## 
## Parameter specification:
##  confidence minval smax arem  aval originalSupport maxtime support minlen
##        0.75    0.1    1 none FALSE            TRUE       5   0.005      1
##  maxlen target  ext
##      10  rules TRUE
## 
## Algorithmic control:
##  filter tree heap memopt load sort verbose
##     0.1 TRUE TRUE  FALSE TRUE    2    TRUE
## 
## Absolute minimum support count: 9 
## 
## set item appearances ...[0 item(s)] done [0.00s].
## set transactions ...[13 item(s), 1968 transaction(s)] done [0.00s].
## sorting and recoding items ... [13 item(s)] done [0.00s].
## creating transaction tree ... done [0.00s].
## checking subsets of size 1 2 3 4 done [0.00s].
## writing ... [49 rule(s)] done [0.00s].
## creating S4 object  ... done [0.00s].

inspect(head(sort(rule2, by = "lift"), 20))

##      lhs                                    rhs                           support confidence    coverage     lift count
## [1]  {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Seat.Type=Premium Economy,                                                                                       
##       Total Rating=[2.57,3.43]}          => {Recommended=no}          0.007621951  0.9375000 0.008130081 1.335988    15
## [2]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=yes,                                                                                                 
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.014227642  0.9655172 0.014735772 1.241109    28
## [3]  {Type.Of.Traveller=Couple Leisure,                                                                                
##       Seat.Type=First Class,                                                                                           
##       Total Rating=[2.57,3.43]}          => {Recommended=no}          0.007113821  0.8235294 0.008638211 1.173574    14
## [4]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[2.57,3.43]}          => {Seat.Type=Economy Class} 0.057926829  0.8837209 0.065548780 1.135965   114
## [5]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Seat.Type=Economy Class,                                                                                         
##       Total Rating=[1.86,2.57)}          => {Recommended=no}          0.056910569  0.7943262 0.071646341 1.131958   112
## [6]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Seat.Type=Premium Economy,                                                                                       
##       Total Rating=[2.57,3.43]}          => {Recommended=no}          0.005589431  0.7857143 0.007113821 1.119686    11
## [7]  {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.060467480  0.8686131 0.069613821 1.116545   119
## [8]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.056910569  0.8682171 0.065548780 1.116036   112
## [9]  {Type.Of.Traveller=Business,                                                                                      
##       Seat.Type=First Class,                                                                                           
##       Total Rating=[1.86,2.57)}          => {Recommended=no}          0.009146341  0.7826087 0.011686992 1.115260    18
## [10] {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[1.86,2.57)}          => {Recommended=no}          0.065548780  0.7818182 0.083841463 1.114133   129
## [11] {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.055386179  0.8650794 0.064024390 1.112003   109
## [12] {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no}                    => {Seat.Type=Economy Class} 0.155995935  0.8647887 0.180386179 1.111629   307
## [13] {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.071646341  0.8545455 0.083841463 1.098462   141
## [14] {Type.Of.Traveller=Family Leisure}  => {Seat.Type=Economy Class} 0.205284553  0.8541226 0.240345528 1.097919   404
## [15] {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[1,1.86)}             => {Recommended=no}          0.049288618  0.7698413 0.064024390 1.097066    97
## [16] {Type.Of.Traveller=Family Leisure,                                                                                
##       Seat.Type=Premium Economy}         => {Recommended=no}          0.011686992  0.7666667 0.015243902 1.092542    23
## [17] {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[2.57,3.43]}          => {Seat.Type=Economy Class} 0.078252033  0.8461538 0.092479675 1.087675   154
## [18] {Type.Of.Traveller=Family Leisure,                                                                                
##       Seat.Type=Economy Class}           => {Recommended=no}          0.155995935  0.7599010 0.205284553 1.082900   307
## [19] {Seat.Type=Premium Economy,                                                                                       
##       Total Rating=[2.57,3.43]}          => {Recommended=no}          0.022357724  0.7586207 0.029471545 1.081076    44
## [20] {Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.170731707  0.8358209 0.204268293 1.074393   336

inspect(head(sort(rule2, by = "confidence"), 20))

##      lhs                                    rhs                           support confidence    coverage     lift count
## [1]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=yes,                                                                                                 
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.014227642  0.9655172 0.014735772 1.241109    28
## [2]  {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Seat.Type=Premium Economy,                                                                                       
##       Total Rating=[2.57,3.43]}          => {Recommended=no}          0.007621951  0.9375000 0.008130081 1.335988    15
## [3]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[2.57,3.43]}          => {Seat.Type=Economy Class} 0.057926829  0.8837209 0.065548780 1.135965   114
## [4]  {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.060467480  0.8686131 0.069613821 1.116545   119
## [5]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.056910569  0.8682171 0.065548780 1.116036   112
## [6]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.055386179  0.8650794 0.064024390 1.112003   109
## [7]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no}                    => {Seat.Type=Economy Class} 0.155995935  0.8647887 0.180386179 1.111629   307
## [8]  {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.071646341  0.8545455 0.083841463 1.098462   141
## [9]  {Type.Of.Traveller=Family Leisure}  => {Seat.Type=Economy Class} 0.205284553  0.8541226 0.240345528 1.097919   404
## [10] {Type.Of.Traveller=Family Leisure,                                                                                
##       Total Rating=[2.57,3.43]}          => {Seat.Type=Economy Class} 0.078252033  0.8461538 0.092479675 1.087675   154
## [11] {Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.170731707  0.8358209 0.204268293 1.074393   336
## [12] {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.041158537  0.8350515 0.049288618 1.073404    81
## [13] {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.085365854  0.8316832 0.102642276 1.069074   168
## [14] {Type.Of.Traveller=Couple Leisure,                                                                                
##       Recommended=no,                                                                                                  
##       Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.042174797  0.8300000 0.050813008 1.066911    83
## [15] {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Recommended=no}                    => {Seat.Type=Economy Class} 0.182926829  0.8275862 0.221036585 1.063808   360
## [16] {Type.Of.Traveller=Solo Leisure,                                                                                  
##       Recommended=no,                                                                                                  
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.057926829  0.8260870 0.070121951 1.061881   114
## [17] {Type.Of.Traveller=Couple Leisure,                                                                                
##       Seat.Type=First Class,                                                                                           
##       Total Rating=[2.57,3.43]}          => {Recommended=no}          0.007113821  0.8235294 0.008638211 1.173574    14
## [18] {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=yes}                   => {Seat.Type=Economy Class} 0.049288618  0.8220339 0.059959350 1.056671    97
## [19] {Total Rating=[1,1.86)}             => {Seat.Type=Economy Class} 0.236280488  0.8086957 0.292174797 1.039525   465
## [20] {Type.Of.Traveller=Family Leisure,                                                                                
##       Recommended=yes,                                                                                                 
##       Total Rating=[1.86,2.57)}          => {Seat.Type=Economy Class} 0.014735772  0.8055556 0.018292683 1.035489    29

plot(rule2)

plot(rule2, method = "grouped")

#Naive Bayesian

# Load required libraries
library(e1071)

## Registered S3 methods overwritten by 'proxy':
##   method               from    
##   print.registry_field registry
##   print.registry_entry registry

library(caTools)
library(caret)

## Loading required package: lattice

## 
## Attaching package: 'caret'

## The following object is masked from 'package:purrr':
## 
##     lift

library(dplyr)
library(gridExtra)
library(class)

reviews <- read.csv("/Users/rahul.chauhan/Desktop/airline_reviews_cleaned.csv", stringsAsFactors = TRUE)

# Select relevant features
features <- c("Type.Of.Traveler", "Seat.Type", "Seat.Comfort", "Cabin.Staff.Services", "Food.Beverages", "Inflight.Entertainment", "Ground.Service", "Wifi", "Value.For.Money")

# Create formula
formula <- as.formula(paste("Recommended ~", paste(features, collapse = "+")))

# Split data into training and testing sets
set.seed(123)
trainIndex <- createDataPartition(reviews$Recommended, p = 0.8, list = FALSE)
trainData <- reviews[trainIndex, ]
testData <- reviews[-trainIndex, ]

# Train Naive Bayes classifier
nb_model <- naiveBayes(formula, data = trainData)

# Make predictions on test data
predictions <- predict(nb_model, testData[, features])
testData$Recommended <- as.factor(testData$Recommended)

# Evaluate performance of model
conf_matrix <- confusionMatrix(predictions, testData$Recommended)
conf_matrix

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction  no yes
##        no  271 113
##        yes   4   1
##                                          
##                Accuracy : 0.6992         
##                  95% CI : (0.651, 0.7444)
##     No Information Rate : 0.7069         
##     P-Value [Acc > NIR] : 0.6541         
##                                          
##                   Kappa : -0.008         
##                                          
##  Mcnemar's Test P-Value : <2e-16         
##                                          
##             Sensitivity : 0.985455       
##             Specificity : 0.008772       
##          Pos Pred Value : 0.705729       
##          Neg Pred Value : 0.200000       
##              Prevalence : 0.706941       
##          Detection Rate : 0.696658       
##    Detection Prevalence : 0.987147       
##       Balanced Accuracy : 0.497113       
##                                          
##        'Positive' Class : no             
## 

conf_df <- as.data.frame(conf_matrix$table)

plot_conf_matrix <- ggplot(data = conf_df, aes(x = Reference, y = Prediction)) +
  geom_tile(aes(fill = Freq), color = "white") +
  scale_fill_gradient(low = "white", high = "steelblue") +
  geom_text(aes(label = Freq)) +
  theme_minimal() +
  labs(x = "Actual", y = "Predicted", title = "Confusion Matrix")

print(plot_conf_matrix)

write.csv(reviews, "/Users/rahul.chauhan/Desktop/airline_reviews_cleaned.csv", row.names=FALSE)

#Decision Trees

mydataset <- read.csv("/Users/rahul.chauhan/Desktop/airline_reviews_cleaned.csv", stringsAsFactors = TRUE)
mydataset$Total.Ratings <- as.integer(mydataset$Total.Ratings)
mydataset <- mydataset[,-c(3,12,13,15,16)]
str(mydataset)

## 'data.frame':    1952 obs. of  11 variables:
##  $ Type.Of.Traveler      : Factor w/ 4 levels "Business","Couple Leisure",..: 3 2 2 2 1 1 4 4 1 3 ...
##  $ Seat.Type             : Factor w/ 4 levels "Business Class",..: 2 2 3 2 3 2 2 2 2 4 ...
##  $ Recommended           : Factor w/ 2 levels "no","yes": 1 2 1 1 1 1 1 2 1 1 ...
##  $ Seat.Comfort          : int  1 2 1 1 4 2 4 1 2 1 ...
##  $ Cabin.Staff.Services  : int  2 3 1 2 5 3 5 2 1 2 ...
##  $ Food.Beverages        : int  3 1 1 3 1 4 1 3 1 1 ...
##  $ Inflight.Entertainment: int  1 2 1 4 2 5 2 4 2 2 ...
##  $ Ground.Service        : int  2 3 1 1 3 1 3 5 3 3 ...
##  $ Wifi                  : int  3 1 1 2 4 2 4 1 1 4 ...
##  $ Value.For.Money       : int  1 2 1 3 1 3 5 1 1 5 ...
##  $ Verification          : Factor w/ 2 levels "Not Verified",..: 2 2 2 1 2 1 1 1 2 2 ...

##Splitting data into training and testing set

set.seed(123) # set a seed for reproducibility
library(caTools) # load the necessary library

options <- c("yes", "no")

# use the sample function to randomly assign "yes" or "no" to each observation since there is a lot of negative feedback in our dataframe than positive, which leads to poor decision tree. Although, the new values may not give effective result, it will produce a decision tree at least.
mydataset$Recommended <- sample(options, size = nrow(mydataset), replace = TRUE)

split_data <- sample.split(mydataset, SplitRatio = 0.9) # split the data into 90% for training and 10% for testing
train_data <- subset(mydataset, split_data == TRUE) # create the training set
test_data <- subset(mydataset, split_data == FALSE) # create the testing set

write.csv(train_data, "/Users/rahul.chauhan/Desktop/train_data.csv", row.names=FALSE)
write.csv(test_data, "/Users/rahul.chauhan/Desktop/test_data.csv", row.names=FALSE)

##First Model

library(rpart)
model1 <- rpart(Recommended ~ ., data = train_data)
# check if the decision tree has more than one node
if(nrow(model1$frame) > 1) {
  plot(model1, margin = 0.1)
  text(model1, cex = 0.7)
} else {
  message("The decision tree has only one node.")
}

pr1 <- predict(model1, newdata = test_data, type="class")

confusionMatrix(table(pred = pr1, true = test_data$Recommended))

## Confusion Matrix and Statistics
## 
##      true
## pred   no yes
##   no   47  49
##   yes 136 122
##                                           
##                Accuracy : 0.4774          
##                  95% CI : (0.4243, 0.5308)
##     No Information Rate : 0.5169          
##     P-Value [Acc > NIR] : 0.9384          
##                                           
##                   Kappa : -0.0292         
##                                           
##  Mcnemar's Test P-Value : 2.568e-10       
##                                           
##             Sensitivity : 0.2568          
##             Specificity : 0.7135          
##          Pos Pred Value : 0.4896          
##          Neg Pred Value : 0.4729          
##              Prevalence : 0.5169          
##          Detection Rate : 0.1328          
##    Detection Prevalence : 0.2712          
##       Balanced Accuracy : 0.4851          
##                                           
##        'Positive' Class : no              
## 

library(rpart.plot)
pruned_tree <- prune.rpart(model1, cp=0)
prp(pruned_tree, faclen=0, extra=1,digits=5)

rpart.plot(model1, box.palette="RdGn", shadow.col="gray", nn=TRUE)

##Second Model

model2 <- rpart(Recommended ~ Type.Of.Traveler + Seat.Type + Verification, data = train_data)
# check if the decision tree has more than one node
if(nrow(model2$frame) > 1) {
  plot(model2, margin = 0.1)
  text(model2, cex = 0.7)
} else {
  message("The decision tree has only one node.")
}

pr2 <- predict(model2, newdata = test_data, type="class")

confusionMatrix(table(pred = pr2, true = test_data$Recommended))

## Confusion Matrix and Statistics
## 
##      true
## pred   no yes
##   no   47  58
##   yes 136 113
##                                           
##                Accuracy : 0.452           
##                  95% CI : (0.3993, 0.5055)
##     No Information Rate : 0.5169          
##     P-Value [Acc > NIR] : 0.9938          
##                                           
##                   Kappa : -0.0811         
##                                           
##  Mcnemar's Test P-Value : 3.234e-08       
##                                           
##             Sensitivity : 0.2568          
##             Specificity : 0.6608          
##          Pos Pred Value : 0.4476          
##          Neg Pred Value : 0.4538          
##              Prevalence : 0.5169          
##          Detection Rate : 0.1328          
##    Detection Prevalence : 0.2966          
##       Balanced Accuracy : 0.4588          
##                                           
##        'Positive' Class : no              
## 

pruned_tree <- prune.rpart(model2, cp=0)
prp(pruned_tree, faclen=0, extra=1,digits=5)

rpart.plot(model2, box.palette="RdGn", shadow.col="gray", nn=TRUE)

##Third Model

set.seed(1234)
options <- c("Verified", "Not Verified")
mydataset$Verification <- sample(options, size = nrow(mydataset), replace = TRUE)

split_data <- sample.split(mydataset, SplitRatio = 0.9) # split the data into 90% for training and 10% for testing
train_data <- subset(mydataset, split_data == TRUE) # create the training set
test_data <- subset(mydataset, split_data == FALSE) # create the testing set

model3 <- rpart(Verification ~ ., data = train_data)
# check if the decision tree has more than one node
if(nrow(model3$frame) > 1) {
  plot(model3, margin = 0.1)
  text(model3, cex = 0.7)
} else {
  message("The decision tree has only one node.")
}

pr3 <- predict(model3, newdata = test_data, type="class")

confusionMatrix(table(pred = pr3, true = test_data$Verification))

## Confusion Matrix and Statistics
## 
##               true
## pred           Not Verified Verified
##   Not Verified           98       97
##   Verified               72       88
##                                           
##                Accuracy : 0.5239          
##                  95% CI : (0.4706, 0.5769)
##     No Information Rate : 0.5211          
##     P-Value [Acc > NIR] : 0.47912         
##                                           
##                   Kappa : 0.0518          
##                                           
##  Mcnemar's Test P-Value : 0.06487         
##                                           
##             Sensitivity : 0.5765          
##             Specificity : 0.4757          
##          Pos Pred Value : 0.5026          
##          Neg Pred Value : 0.5500          
##              Prevalence : 0.4789          
##          Detection Rate : 0.2761          
##    Detection Prevalence : 0.5493          
##       Balanced Accuracy : 0.5261          
##                                           
##        'Positive' Class : Not Verified    
## 

pruned_tree <- prune.rpart(model3, cp=0)
prp(pruned_tree, faclen=0, extra=1,digits=5)

rpart.plot(model3, box.palette="RdGn", shadow.col="gray", nn=TRUE)

#SVM

library(e1071)
#We need only labeled numeric data for SVMs, let's look at our dataframe to check for numeric labelled entries. Also, check for data that can be converted to numeric type.
reviews <- read.csv("/Users/rahul.chauhan/Desktop/airline_reviews_cleaned.csv", stringsAsFactors = TRUE)

# Here, we can see that we have "Seat Comfort", "Cabin Staff Services", "Food & Beverages", "Inflight Entertainment", "Ground Service", "Wifi", "Value for money", "Total Ratings" which are labeled and numeric.

# We can also convert "Verification", "Type of Traveler, "Seat Type" and "Recommended" to numeric.
# "Origin", "Destination", "Reviews", "Date flown" cannot be used for SVMs.

reviews_svm <- as.data.frame(reviews)
reviews_svm <- reviews_svm[ ,-c(3,12,14,15,16)]
sapply(reviews_svm, class)

##       Type.Of.Traveler              Seat.Type            Recommended 
##               "factor"               "factor"               "factor" 
##           Seat.Comfort   Cabin.Staff.Services         Food.Beverages 
##              "integer"              "integer"              "integer" 
## Inflight.Entertainment         Ground.Service                   Wifi 
##              "integer"              "integer"              "integer" 
##        Value.For.Money          Total.Ratings 
##              "integer"              "numeric"

reviews_svm$Type.Of.Traveler <- as.numeric(reviews$Type.Of.Traveler)
reviews_svm$Seat.Type <- as.numeric(reviews_svm$Seat.Type)
sapply(reviews_svm, class)

##       Type.Of.Traveler              Seat.Type            Recommended 
##              "numeric"              "numeric"               "factor" 
##           Seat.Comfort   Cabin.Staff.Services         Food.Beverages 
##              "integer"              "integer"              "integer" 
## Inflight.Entertainment         Ground.Service                   Wifi 
##              "integer"              "integer"              "integer" 
##        Value.For.Money          Total.Ratings 
##              "integer"              "numeric"

str(reviews_svm)

## 'data.frame':    1952 obs. of  11 variables:
##  $ Type.Of.Traveler      : num  3 2 2 2 1 1 4 4 1 3 ...
##  $ Seat.Type             : num  2 2 3 2 3 2 2 2 2 4 ...
##  $ Recommended           : Factor w/ 2 levels "no","yes": 1 2 1 1 1 1 1 2 1 1 ...
##  $ Seat.Comfort          : int  1 2 1 1 4 2 4 1 2 1 ...
##  $ Cabin.Staff.Services  : int  2 3 1 2 5 3 5 2 1 2 ...
##  $ Food.Beverages        : int  3 1 1 3 1 4 1 3 1 1 ...
##  $ Inflight.Entertainment: int  1 2 1 4 2 5 2 4 2 2 ...
##  $ Ground.Service        : int  2 3 1 1 3 1 3 5 3 3 ...
##  $ Wifi                  : int  3 1 1 2 4 2 4 1 1 4 ...
##  $ Value.For.Money       : int  1 2 1 3 1 3 5 1 1 5 ...
##  $ Total.Ratings         : num  1.86 2 1 2.29 2.86 ...

head(reviews_svm)

##   Type.Of.Traveler Seat.Type Recommended Seat.Comfort Cabin.Staff.Services
## 1                3         2          no            1                    2
## 2                2         2         yes            2                    3
## 3                2         3          no            1                    1
## 4                2         2          no            1                    2
## 5                1         3          no            4                    5
## 6                1         2          no            2                    3
##   Food.Beverages Inflight.Entertainment Ground.Service Wifi Value.For.Money
## 1              3                      1              2    3               1
## 2              1                      2              3    1               2
## 3              1                      1              1    1               1
## 4              3                      4              1    2               3
## 5              1                      2              3    4               1
## 6              4                      5              1    2               3
##   Total.Ratings
## 1      1.857143
## 2      2.000000
## 3      1.000000
## 4      2.285714
## 5      2.857143
## 6      2.857143

##Linear Kernel with traditional method

library(e1071)
set.seed(123)
split_data <- sample.split(reviews_svm, SplitRatio = 0.9) # split the data into 90% for training and 10% for testing
train <- subset(reviews_svm, split_data == TRUE) # create the training set
test <- subset(reviews_svm, split_data == FALSE) # create the testing set

svm_linear <- svm(Recommended ~ ., data = train, kernel = "linear")

svm_linear_pred <- predict(svm_linear, test)

svm_linear_cm <- confusionMatrix(svm_linear_pred, test$Recommended)

svm_linear_accuracy <- svm_linear_cm$overall["Accuracy"]
print("Confusion matrix for SVM with linear kernel:")

## [1] "Confusion matrix for SVM with linear kernel:"

print(svm_linear_cm$table)

##           Reference
## Prediction  no yes
##        no  240 115
##        yes   0   0

print(paste("Accuracy:", svm_linear_accuracy))

## [1] "Accuracy: 0.676056338028169"

# plot the SVM with linear kernel
plot(svm_linear, reviews_svm, Total.Ratings ~ Type.Of.Traveler)

##Polynomial Kernel with traditional method

svm_poly <- svm(Recommended ~ ., data = train, kernel = "polynomial", degree = 3)

svm_poly_pred <- predict(svm_poly, test)

svm_poly_cm <- confusionMatrix(svm_poly_pred, test$Recommended)

svm_poly_accuracy <- svm_poly_cm$overall["Accuracy"]
print("Confusion matrix for SVM with polynomial kernel:")

## [1] "Confusion matrix for SVM with polynomial kernel:"

print(svm_poly_cm$table)

##           Reference
## Prediction  no yes
##        no  240 115
##        yes   0   0

print(paste("Accuracy:", svm_poly_accuracy))

## [1] "Accuracy: 0.676056338028169"

plot(svm_poly, reviews_svm, Total.Ratings ~ Type.Of.Traveler)

##Radial Kernel with traditional method

svm_radial <- svm(Recommended ~ ., data = train, kernel = "radial")

svm_radial_pred <- predict(svm_radial, test)

svm_radial_cm <- confusionMatrix(svm_radial_pred, test$Recommended)

svm_radial_accuracy <- svm_radial_cm$overall["Accuracy"]

print("Confusion matrix for SVM with radial kernel:")

## [1] "Confusion matrix for SVM with radial kernel:"

print(svm_radial_cm$table)

##           Reference
## Prediction  no yes
##        no  240 115
##        yes   0   0

print(paste("Accuracy:", svm_radial_accuracy))

## [1] "Accuracy: 0.676056338028169"

plot(svm_radial, reviews_svm, Total.Ratings ~ Type.Of.Traveler)

#All the kernel using three different costs for each

library(e1071)
set.seed(42)
ind <- sample(2, nrow(reviews_svm), replace = TRUE, prob = c(0.9, 0.1))
train_data <- reviews_svm[ind == 1,]
test_data <- reviews_svm[ind == 2,]

write.csv(train_data, "/Users/rahul.chauhan/Desktop/train_data_svm.csv", row.names=FALSE)
write.csv(test_data, "/Users/rahul.chauhan/Desktop/test_data_svm.csv", row.names=FALSE)
kernels <- c("linear", "polynomial", "radial")
costs <- c(0.1, 1, 10)
fit_svm <- function(kernel, cost) {
  model <- svm(Recommended ~ ., data = train_data, kernel = kernel, cost = cost)
  preds <- predict(model, test_data)
  accuracy <- sum(preds == test_data$Recommended) / length(preds)
  cm <- table(Predicted = preds, Actual = test_data$Recommended)
  
  plot(model, train_data, Seat.Type ~ Seat.Comfort, main = paste("Kernel:", kernel, ", Cost:", cost))
  cat("Kernel:", kernel, ", Cost:", cost, "\n")
  cat("Accuracy:", accuracy, "\n")
  cat("Confusion Matrix:\n")
  print(cm)
  cat("\n")
}
for (kernel in kernels) {
  for (cost in costs) {
    fit_svm(kernel, cost)
  }
}

## Kernel: linear , Cost: 0.1 
## Accuracy: 0.7156398 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  151  60
##       yes   0   0

## Kernel: linear , Cost: 1 
## Accuracy: 0.7156398 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  151  60
##       yes   0   0

## Kernel: linear , Cost: 10 
## Accuracy: 0.7156398 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  151  60
##       yes   0   0

## Kernel: polynomial , Cost: 0.1 
## Accuracy: 0.7156398 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  151  60
##       yes   0   0

## Kernel: polynomial , Cost: 1 
## Accuracy: 0.7156398 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  151  60
##       yes   0   0

## Kernel: polynomial , Cost: 10 
## Accuracy: 0.7156398 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  151  60
##       yes   0   0

## Kernel: radial , Cost: 0.1 
## Accuracy: 0.7156398 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  151  60
##       yes   0   0

## Kernel: radial , Cost: 1 
## Accuracy: 0.7156398 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  151  60
##       yes   0   0

## Kernel: radial , Cost: 10 
## Accuracy: 0.7061611 
## Confusion Matrix:
##          Actual
## Predicted  no yes
##       no  147  58
##       yes   4   2